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>

drivers/acpi/apei/cper.c

@@ -29,6 +29,7 @@
 #include <linux/time.h>
 #include <linux/cper.h>
 #include <linux/acpi.h>
+#include <linux/pci.h>
 #include <linux/aer.h>
 
 /*
@@ -249,6 +250,10 @@ static const char *cper_pcie_port_type_strs[] = {
 static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 			    const struct acpi_hest_generic_data *gdata)
 {
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+	struct pci_dev *dev;
+#endif
+
 	if (pcie->validation_bits & CPER_PCIE_VALID_PORT_TYPE)
 		printk("%s""port_type: %d, %s\n", pfx, pcie->port_type,
 		       pcie->port_type < ARRAY_SIZE(cper_pcie_port_type_strs) ?
@@ -281,10 +286,18 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 	"%s""bridge: secondary_status: 0x%04x, control: 0x%04x\n",
 	pfx, pcie->bridge.secondary_status, pcie->bridge.control);
 #ifdef CONFIG_ACPI_APEI_PCIEAER
-	if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO) {
-		struct aer_capability_regs *aer_regs = (void *)pcie->aer_info;
-		cper_print_aer(pfx, gdata->error_severity, aer_regs);
+	dev = pci_get_domain_bus_and_slot(pcie->device_id.segment,
+			pcie->device_id.bus, pcie->device_id.function);
+	if (!dev) {
+		pr_err("PCI AER Cannot get PCI device %04x:%02x:%02x.%d\n",
+			pcie->device_id.segment, pcie->device_id.bus,
+			pcie->device_id.slot, pcie->device_id.function);
+		return;
 	}
+	if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO)
+		cper_print_aer(pfx, dev, gdata->error_severity,
+				(struct aer_capability_regs *) pcie->aer_info);
+	pci_dev_put(dev);
 #endif
 }
 

drivers/pci/pcie/aer/aerdrv_errprint.c

@@ -23,6 +23,9 @@
 
 #include "aerdrv.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/ras.h>
+
 #define AER_AGENT_RECEIVER		0
 #define AER_AGENT_REQUESTER		1
 #define AER_AGENT_COMPLETER		2
@@ -121,12 +124,11 @@ static const char *aer_agent_string[] = {
 	"Transmitter ID"
 };
 
-static void __aer_print_error(const char *prefix,
+static void __aer_print_error(struct pci_dev *dev,
 			      struct aer_err_info *info)
 {
 	int i, status;
 	const char *errmsg = NULL;
-
 	status = (info->status & ~info->mask);
 
 	for (i = 0; i < 32; i++) {
@@ -141,26 +143,22 @@ static void __aer_print_error(const char *prefix,
 				aer_uncorrectable_error_string[i] : NULL;
 
 		if (errmsg)
-			printk("%s""   [%2d] %-22s%s\n", prefix, i, errmsg,
+			dev_err(&dev->dev, "   [%2d] %-22s%s\n", i, errmsg,
 				info->first_error == i ? " (First)" : "");
 		else
-			printk("%s""   [%2d] Unknown Error Bit%s\n", prefix, i,
-				info->first_error == i ? " (First)" : "");
+			dev_err(&dev->dev, "   [%2d] Unknown Error Bit%s\n",
+				i, info->first_error == i ? " (First)" : "");
 	}
 }
 
 void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 {
 	int id = ((dev->bus->number << 8) | dev->devfn);
-	char prefix[44];
-
-	snprintf(prefix, sizeof(prefix), "%s%s %s: ",
-		 (info->severity == AER_CORRECTABLE) ? KERN_WARNING : KERN_ERR,
-		 dev_driver_string(&dev->dev), dev_name(&dev->dev));
 
 	if (info->status == 0) {
-		printk("%s""PCIe Bus Error: severity=%s, type=Unaccessible, "
-			"id=%04x(Unregistered Agent ID)\n", prefix,
+		dev_err(&dev->dev,
+			"PCIe Bus Error: severity=%s, type=Unaccessible, "
+			"id=%04x(Unregistered Agent ID)\n",
 			aer_error_severity_string[info->severity], id);
 	} else {
 		int layer, agent;
@@ -168,22 +166,24 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 		layer = AER_GET_LAYER_ERROR(info->severity, info->status);
 		agent = AER_GET_AGENT(info->severity, info->status);
 
-		printk("%s""PCIe Bus Error: severity=%s, type=%s, id=%04x(%s)\n",
-			prefix, aer_error_severity_string[info->severity],
+		dev_err(&dev->dev,
+			"PCIe Bus Error: severity=%s, type=%s, id=%04x(%s)\n",
+			aer_error_severity_string[info->severity],
 			aer_error_layer[layer], id, aer_agent_string[agent]);
 
-		printk("%s""  device [%04x:%04x] error status/mask=%08x/%08x\n",
-			prefix, dev->vendor, dev->device,
+		dev_err(&dev->dev,
+			"  device [%04x:%04x] error status/mask=%08x/%08x\n",
+			dev->vendor, dev->device,
 			info->status, info->mask);
 
-		__aer_print_error(prefix, info);
+		__aer_print_error(dev, info);
 
 		if (info->tlp_header_valid) {
 			unsigned char *tlp = (unsigned char *) &info->tlp;
-			printk("%s""  TLP Header:"
+			dev_err(&dev->dev, "  TLP Header:"
 				" %02x%02x%02x%02x %02x%02x%02x%02x"
 				" %02x%02x%02x%02x %02x%02x%02x%02x\n",
-				prefix, *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp,
+				*(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp,
 				*(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4),
 				*(tlp + 11), *(tlp + 10), *(tlp + 9),
 				*(tlp + 8), *(tlp + 15), *(tlp + 14),
@@ -192,8 +192,11 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 	}
 
 	if (info->id && info->error_dev_num > 1 && info->id == id)
-		printk("%s""  Error of this Agent(%04x) is reported first\n",
-			prefix, id);
+		dev_err(&dev->dev,
+			   "  Error of this Agent(%04x) is reported first\n",
+			id);
+	trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
+			info->severity);
 }
 
 void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
@@ -217,7 +220,7 @@ int cper_severity_to_aer(int cper_severity)
 }
 EXPORT_SYMBOL_GPL(cper_severity_to_aer);
 
-void cper_print_aer(const char *prefix, int cper_severity,
+void cper_print_aer(const char *prefix, struct pci_dev *dev, int cper_severity,
 		    struct aer_capability_regs *aer)
 {
 	int aer_severity, layer, agent, status_strs_size, tlp_header_valid = 0;
@@ -239,25 +242,27 @@ void cper_print_aer(const char *prefix, int cper_severity,
 	}
 	layer = AER_GET_LAYER_ERROR(aer_severity, status);
 	agent = AER_GET_AGENT(aer_severity, status);
-	printk("%s""aer_status: 0x%08x, aer_mask: 0x%08x\n",
-	       prefix, status, mask);
+	dev_err(&dev->dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n",
+	       status, mask);
 	cper_print_bits(prefix, status, status_strs, status_strs_size);
-	printk("%s""aer_layer=%s, aer_agent=%s\n", prefix,
+	dev_err(&dev->dev, "aer_layer=%s, aer_agent=%s\n",
 	       aer_error_layer[layer], aer_agent_string[agent]);
 	if (aer_severity != AER_CORRECTABLE)
-		printk("%s""aer_uncor_severity: 0x%08x\n",
-		       prefix, aer->uncor_severity);
+		dev_err(&dev->dev, "aer_uncor_severity: 0x%08x\n",
+		       aer->uncor_severity);
 	if (tlp_header_valid) {
 		const unsigned char *tlp;
 		tlp = (const unsigned char *)&aer->header_log;
-		printk("%s""aer_tlp_header:"
+		dev_err(&dev->dev, "aer_tlp_header:"
 			" %02x%02x%02x%02x %02x%02x%02x%02x"
 			" %02x%02x%02x%02x %02x%02x%02x%02x\n",
-			prefix, *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp,
+			*(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp,
 			*(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4),
 			*(tlp + 11), *(tlp + 10), *(tlp + 9),
 			*(tlp + 8), *(tlp + 15), *(tlp + 14),
 			*(tlp + 13), *(tlp + 12));
 	}
+	trace_aer_event(dev_name(&dev->dev), (status & ~mask),
+			aer_severity);
 }
 #endif

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>