aerdrv: Enhanced AER logging

This patch will provide a more reliable and easy way for user-space
applications to have access to AER logs rather than reading them from the
message buffer. It also provides a way to notify user-space when an AER
event occurs.

The aer driver is updated to generate a trace event of function 'aer_event'
when a PCIe error is reported over the AER interface.  The trace event was
added to both the interrupt based aer path and the firmware first path.

Signed-off-by: Lance Ortiz <lance.ortiz@hp.com>
Acked-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Acked-by: Boris Petkov <bp@alien8.de>
Signed-off-by: Tony Luck <tony.luck@intel.com>

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
@@ -194,6 +197,8 @@ 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);
+	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 +222,7 @@ 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;
@@ -259,5 +264,7 @@ void cper_print_aer(const char *prefix, int cper_severity,
 			*(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);