PCI/AER: Add sysfs attributes to provide AER stats and breakdown

Add sysfs attributes to provide total and breakdown of the AERs seen,
into different type of correctable, fatal and nonfatal errors:

  /sys/bus/pci/devices/<dev>/aer_dev_correctable
  /sys/bus/pci/devices/<dev>/aer_dev_fatal
  /sys/bus/pci/devices/<dev>/aer_dev_nonfatal
Signed-off-by: Rajat Jain <rajatja@google.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>

Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats

+==========================
+PCIe Device AER statistics
+==========================
+These attributes show up under all the devices that are AER capable. These
+statistical counters indicate the errors "as seen/reported by the device".
+Note that this may mean that if an endpoint is causing problems, the AER
+counters may increment at its link partner (e.g. root port) because the
+errors may be "seen" / reported by the link partner and not the
+problematic endpoint itself (which may report all counters as 0 as it never
+saw any problems).
+
+Where:		/sys/bus/pci/devices/<dev>/aer_dev_correctable
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	List of correctable errors seen and reported by this
+		PCI device using ERR_COR. Note that since multiple errors may
+		be reported using a single ERR_COR message, thus
+		TOTAL_ERR_COR at the end of the file may not match the actual
+		total of all the errors in the file. Sample output:
+-------------------------------------------------------------------------
+localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_correctable
+Receiver Error 2
+Bad TLP 0
+Bad DLLP 0
+RELAY_NUM Rollover 0
+Replay Timer Timeout 0
+Advisory Non-Fatal 0
+Corrected Internal Error 0
+Header Log Overflow 0
+TOTAL_ERR_COR 2
+-------------------------------------------------------------------------
+
+Where:		/sys/bus/pci/devices/<dev>/aer_dev_fatal
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	List of uncorrectable fatal errors seen and reported by this
+		PCI device using ERR_FATAL. Note that since multiple errors may
+		be reported using a single ERR_FATAL message, thus
+		TOTAL_ERR_FATAL at the end of the file may not match the actual
+		total of all the errors in the file. Sample output:
+-------------------------------------------------------------------------
+localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_fatal
+Undefined 0
+Data Link Protocol 0
+Surprise Down Error 0
+Poisoned TLP 0
+Flow Control Protocol 0
+Completion Timeout 0
+Completer Abort 0
+Unexpected Completion 0
+Receiver Overflow 0
+Malformed TLP 0
+ECRC 0
+Unsupported Request 0
+ACS Violation 0
+Uncorrectable Internal Error 0
+MC Blocked TLP 0
+AtomicOp Egress Blocked 0
+TLP Prefix Blocked Error 0
+TOTAL_ERR_FATAL 0
+-------------------------------------------------------------------------
+
+Where:		/sys/bus/pci/devices/<dev>/aer_dev_nonfatal
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	List of uncorrectable nonfatal errors seen and reported by this
+		PCI device using ERR_NONFATAL. Note that since multiple errors
+		may be reported using a single ERR_FATAL message, thus
+		TOTAL_ERR_NONFATAL at the end of the file may not match the
+		actual total of all the errors in the file. Sample output:
+-------------------------------------------------------------------------
+localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_nonfatal
+Undefined 0
+Data Link Protocol 0
+Surprise Down Error 0
+Poisoned TLP 0
+Flow Control Protocol 0
+Completion Timeout 0
+Completer Abort 0
+Unexpected Completion 0
+Receiver Overflow 0
+Malformed TLP 0
+ECRC 0
+Unsupported Request 0
+ACS Violation 0
+Uncorrectable Internal Error 0
+MC Blocked TLP 0
+AtomicOp Egress Blocked 0
+TLP Prefix Blocked Error 0
+TOTAL_ERR_NONFATAL 0
+-------------------------------------------------------------------------

Documentation/PCI/pcieaer-howto.txt

@@ -73,6 +73,11 @@ In the example, 'Requester ID' means the ID of the device who sends
 the error message to root port. Pls. refer to pci express specs for
 other fields.
 
+2.4 AER Statistics / Counters
+
+When PCIe AER errors are captured, the counters / statistics are also exposed
+in the form of sysfs attributes which are documented at
+Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
 
 3. Developer Guide
 

drivers/pci/pci-sysfs.c

@@ -1746,6 +1746,9 @@ static const struct attribute_group *pci_dev_attr_groups[] = {
 #endif
 	&pci_bridge_attr_group,
 	&pcie_dev_attr_group,
+#ifdef CONFIG_PCIEAER
+	&aer_stats_attr_group,
+#endif
 	NULL,
 };
 

drivers/pci/pci.h

@@ -484,6 +484,7 @@ static inline int devm_of_pci_get_host_bridge_resources(struct device *dev,
 void pci_no_aer(void);
 void pci_aer_init(struct pci_dev *dev);
 void pci_aer_exit(struct pci_dev *dev);
+extern const struct attribute_group aer_stats_attr_group;
 #else
 static inline void pci_no_aer(void) { }
 static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; }

drivers/pci/pcie/aer.c

@@ -542,6 +542,99 @@ static const char *aer_agent_string[] = {
 	"Transmitter ID"
 };
 
+#define aer_stats_dev_attr(name, stats_array, strings_array,		\
+			   total_string, total_field)			\
+	static ssize_t							\
+	name##_show(struct device *dev, struct device_attribute *attr,	\
+		     char *buf)						\
+{									\
+	unsigned int i;							\
+	char *str = buf;						\
+	struct pci_dev *pdev = to_pci_dev(dev);				\
+	u64 *stats = pdev->aer_stats->stats_array;			\
+									\
+	for (i = 0; i < ARRAY_SIZE(strings_array); i++) {		\
+		if (strings_array[i])					\
+			str += sprintf(str, "%s %llu\n",		\
+				       strings_array[i], stats[i]);	\
+		else if (stats[i])					\
+			str += sprintf(str, #stats_array "_bit[%d] %llu\n",\
+				       i, stats[i]);			\
+	}								\
+	str += sprintf(str, "TOTAL_%s %llu\n", total_string,		\
+		       pdev->aer_stats->total_field);			\
+	return str-buf;							\
+}									\
+static DEVICE_ATTR_RO(name)
+
+aer_stats_dev_attr(aer_dev_correctable, dev_cor_errs,
+		   aer_correctable_error_string, "ERR_COR",
+		   dev_total_cor_errs);
+aer_stats_dev_attr(aer_dev_fatal, dev_fatal_errs,
+		   aer_uncorrectable_error_string, "ERR_FATAL",
+		   dev_total_fatal_errs);
+aer_stats_dev_attr(aer_dev_nonfatal, dev_nonfatal_errs,
+		   aer_uncorrectable_error_string, "ERR_NONFATAL",
+		   dev_total_nonfatal_errs);
+
+static struct attribute *aer_stats_attrs[] __ro_after_init = {
+	&dev_attr_aer_dev_correctable.attr,
+	&dev_attr_aer_dev_fatal.attr,
+	&dev_attr_aer_dev_nonfatal.attr,
+	NULL
+};
+
+static umode_t aer_stats_attrs_are_visible(struct kobject *kobj,
+					   struct attribute *a, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	if (!pdev->aer_stats)
+		return 0;
+
+	return a->mode;
+}
+
+const struct attribute_group aer_stats_attr_group = {
+	.attrs  = aer_stats_attrs,
+	.is_visible = aer_stats_attrs_are_visible,
+};
+
+static void pci_dev_aer_stats_incr(struct pci_dev *pdev,
+				   struct aer_err_info *info)
+{
+	int status, i, max = -1;
+	u64 *counter = NULL;
+	struct aer_stats *aer_stats = pdev->aer_stats;
+
+	if (!aer_stats)
+		return;
+
+	switch (info->severity) {
+	case AER_CORRECTABLE:
+		aer_stats->dev_total_cor_errs++;
+		counter = &aer_stats->dev_cor_errs[0];
+		max = AER_MAX_TYPEOF_COR_ERRS;
+		break;
+	case AER_NONFATAL:
+		aer_stats->dev_total_nonfatal_errs++;
+		counter = &aer_stats->dev_nonfatal_errs[0];
+		max = AER_MAX_TYPEOF_UNCOR_ERRS;
+		break;
+	case AER_FATAL:
+		aer_stats->dev_total_fatal_errs++;
+		counter = &aer_stats->dev_fatal_errs[0];
+		max = AER_MAX_TYPEOF_UNCOR_ERRS;
+		break;
+	}
+
+	status = (info->status & ~info->mask);
+	for (i = 0; i < max; i++)
+		if (status & (1 << i))
+			counter[i]++;
+}
+
 static void __print_tlp_header(struct pci_dev *dev,
 			       struct aer_header_log_regs *t)
 {
@@ -574,6 +667,7 @@ static void __aer_print_error(struct pci_dev *dev,
 			pci_err(dev, "   [%2d] Unknown Error Bit%s\n",
 				i, info->first_error == i ? " (First)" : "");
 	}
+	pci_dev_aer_stats_incr(dev, info);
 }
 
 void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)