PCI/AER: Report CXL or PCIe bus type in AER trace logging

The AER service driver and aer_event tracing currently log 'PCIe Bus Type'
for all errors. Update the driver and aer_event tracing to log 'CXL Bus
Type' for CXL device errors.

This requires that AER can identify and distinguish between PCIe errors and
CXL errors.

Introduce boolean 'is_cxl' to 'struct aer_err_info'. Add assignment in
aer_get_device_error_info() and pci_print_aer().

Update the aer_event trace routine to accept a bus type string parameter.

Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Co-developed-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Link: https://patch.msgid.link/20260114182055.46029-15-terry.bowman@amd.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>

3 files changed, 28 insertions, 12 deletions

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 0e67014aa001..41ec38e82c08 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -738,7 +738,8 @@ struct aer_err_info {
 	unsigned int multi_error_valid:1;
 
 	unsigned int first_error:5;
-	unsigned int __pad2:2;
+	unsigned int __pad2:1;
+	unsigned int is_cxl:1;
 	unsigned int tlp_header_valid:1;
 
 	unsigned int status;		/* COR/UNCOR Error Status */
@@ -749,6 +750,11 @@ struct aer_err_info {
 int aer_get_device_error_info(struct aer_err_info *info, int i);
 void aer_print_error(struct aer_err_info *info, int i);
 
+static inline const char *aer_err_bus(struct aer_err_info *info)
+{
+	return info->is_cxl ? "CXL" : "PCIe";
+}
+
 int pcie_read_tlp_log(struct pci_dev *dev, int where, int where2,
 		      unsigned int tlp_len, bool flit,
 		      struct pcie_tlp_log *log);
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index ff499fd4a322..49a4bd13c2d2 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -870,6 +870,7 @@ void aer_print_error(struct aer_err_info *info, int i)
 	struct pci_dev *dev;
 	int layer, agent, id;
 	const char *level = info->level;
+	const char *bus_type = aer_err_bus(info);
 
 	if (WARN_ON_ONCE(i >= AER_MAX_MULTI_ERR_DEVICES))
 		return;
@@ -879,22 +880,22 @@ void aer_print_error(struct aer_err_info *info, int i)
 
 	pci_dev_aer_stats_incr(dev, info);
 	trace_aer_event(pci_name(dev), (info->status & ~info->mask),
-			info->severity, info->tlp_header_valid, &info->tlp);
+			info->severity, info->tlp_header_valid, &info->tlp, bus_type);
 
 	if (!info->ratelimit_print[i])
 		return;
 
 	if (!info->status) {
-		pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
-			aer_error_severity_string[info->severity]);
+		pci_err(dev, "%s Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
+			bus_type, aer_error_severity_string[info->severity]);
 		goto out;
 	}
 
 	layer = AER_GET_LAYER_ERROR(info->severity, info->status);
 	agent = AER_GET_AGENT(info->severity, info->status);
 
-	aer_printk(level, dev, "PCIe Bus Error: severity=%s, type=%s, (%s)\n",
-		   aer_error_severity_string[info->severity],
+	aer_printk(level, dev, "%s Bus Error: severity=%s, type=%s, (%s)\n",
+		   bus_type, aer_error_severity_string[info->severity],
 		   aer_error_layer[layer], aer_agent_string[agent]);
 
 	aer_printk(level, dev, "  device [%04x:%04x] error status/mask=%08x/%08x\n",
@@ -928,6 +929,7 @@ EXPORT_SYMBOL_GPL(cper_severity_to_aer);
 void pci_print_aer(struct pci_dev *dev, int aer_severity,
 		   struct aer_capability_regs *aer)
 {
+	const char *bus_type;
 	int layer, agent, tlp_header_valid = 0;
 	u32 status, mask;
 	struct aer_err_info info = {
@@ -948,10 +950,13 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
 
 	info.status = status;
 	info.mask = mask;
+	info.is_cxl = pcie_is_cxl(dev);
+
+	bus_type = aer_err_bus(&info);
 
 	pci_dev_aer_stats_incr(dev, &info);
-	trace_aer_event(pci_name(dev), (status & ~mask),
-			aer_severity, tlp_header_valid, &aer->header_log);
+	trace_aer_event(pci_name(dev), (status & ~mask), aer_severity,
+			tlp_header_valid, &aer->header_log, bus_type);
 
 	if (!aer_ratelimit(dev, info.severity))
 		return;
@@ -1306,6 +1311,7 @@ int aer_get_device_error_info(struct aer_err_info *info, int i)
 	/* Must reset in this function */
 	info->status = 0;
 	info->tlp_header_valid = 0;
+	info->is_cxl = pcie_is_cxl(dev);
 
 	/* The device might not support AER */
 	if (!aer)
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index eaecc3c5f772..fdb785fa4613 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -339,9 +339,11 @@ TRACE_EVENT(aer_event,
 		 const u32 status,
 		 const u8 severity,
 		 const u8 tlp_header_valid,
-		 struct pcie_tlp_log *tlp),
+		 struct pcie_tlp_log *tlp,
+		 const char *bus_type),
 
-	TP_ARGS(dev_name, status, severity, tlp_header_valid, tlp),
+
+	TP_ARGS(dev_name, status, severity, tlp_header_valid, tlp, bus_type),
 
 	TP_STRUCT__entry(
 		__string(	dev_name,	dev_name	)
@@ -349,10 +351,12 @@ TRACE_EVENT(aer_event,
 		__field(	u8,		severity	)
 		__field(	u8, 		tlp_header_valid)
 		__array(	u32, 		tlp_header, PCIE_STD_MAX_TLP_HEADERLOG)
+		__string(	bus_type,	bus_type	)
 	),
 
 	TP_fast_assign(
 		__assign_str(dev_name);
+		__assign_str(bus_type);
 		__entry->status		= status;
 		__entry->severity	= severity;
 		__entry->tlp_header_valid = tlp_header_valid;
@@ -364,8 +368,8 @@ TRACE_EVENT(aer_event,
 		}
 	),
 
-	TP_printk("%s PCIe Bus Error: severity=%s, %s, TLP Header=%s\n",
-		__get_str(dev_name),
+	TP_printk("%s %s Bus Error: severity=%s, %s, TLP Header=%s\n",
+		__get_str(dev_name), __get_str(bus_type),
 		__entry->severity == AER_CORRECTABLE ? "Corrected" :
 			__entry->severity == AER_FATAL ?
 			"Fatal" : "Uncorrected, non-fatal",