On 2/11/2025 6:21 PM, Dave Jiang wrote:
>
> On 2/11/25 12:24 PM, Terry Bowman wrote:
>> CXL RAS errors are currently logged using the associated CXL port's name
>> returned from devname(). They are typically named with 'port1', 'port2',
>> etc. to indicate the hierarchial location in the CXL topology. But, this
>> doesn't clearly indicate the CXL card or slot reporting the error.
>>
>> Update the logging to also log the corresponding PCIe devname. This will
>> give a PCIe SBDF or ACPI object name (in case of CXL HB). This will provide
>> details helping users understand which physical slot and card has the
>> error.
>>
>> Below is example output after making these changes.
>>
>> Correctable error example output:
>> cxl_port_aer_correctable_error: device=port1 (0000:0c:00.0) parent=root0 (pci0000:0c) status='Received Error From Physical Layer'
>>
>> Uncorrectable error example output:
>> cxl_port_aer_uncorrectable_error: device=port1 (0000:0c:00.0) parent=root0 (pci0000:0c) status: 'Memory Byte Enable Parity Error' first_error: 'Memory Byte Enable Parity Error'
>>
>> Signed-off-by: Terry Bowman <terry.bowman@xxxxxxx>
> I wonder if there's any benefit in identifying if the PCIe device is USP or DSP...
>
> Reviewed-by: Dave Jiang <dave.jiang@xxxxxxxxx>
That would be nice for the user. I'll add it to the TODO list.
Thanks for reviewing.
Terry
>> ---
>> drivers/cxl/core/pci.c | 39 +++++++++++++++++++------------------
>> drivers/cxl/core/trace.h | 42 +++++++++++++++++++++++++---------------
>> 2 files changed, 46 insertions(+), 35 deletions(-)
>>
>> diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
>> index 9a3090dae46a..f154dcf6dfda 100644
>> --- a/drivers/cxl/core/pci.c
>> +++ b/drivers/cxl/core/pci.c
>> @@ -652,14 +652,14 @@ void read_cdat_data(struct cxl_port *port)
>> }
>> EXPORT_SYMBOL_NS_GPL(read_cdat_data, "CXL");
>>
>> -static void __cxl_handle_cor_ras(struct device *dev,
>> +static void __cxl_handle_cor_ras(struct device *cxl_dev, struct device *pcie_dev,
>> void __iomem *ras_base)
>> {
>> void __iomem *addr;
>> u32 status;
>>
>> if (!ras_base) {
>> - dev_warn_once(dev, "CXL RAS register block is not mapped");
>> + dev_warn_once(cxl_dev, "CXL RAS register block is not mapped");
>> return;
>> }
>>
>> @@ -669,15 +669,15 @@ static void __cxl_handle_cor_ras(struct device *dev,
>> return;
>> writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr);
>>
>> - if (is_cxl_memdev(dev))
>> - trace_cxl_aer_correctable_error(to_cxl_memdev(dev), status);
>> - else if (is_cxl_port(dev))
>> - trace_cxl_port_aer_correctable_error(dev, status);
>> + if (is_cxl_memdev(cxl_dev))
>> + trace_cxl_aer_correctable_error(to_cxl_memdev(cxl_dev), status);
>> + else if (is_cxl_port(cxl_dev))
>> + trace_cxl_port_aer_correctable_error(cxl_dev, pcie_dev, status);
>> }
>>
>> static void cxl_handle_endpoint_cor_ras(struct cxl_dev_state *cxlds)
>> {
>> - return __cxl_handle_cor_ras(&cxlds->cxlmd->dev, cxlds->regs.ras);
>> + return __cxl_handle_cor_ras(&cxlds->cxlmd->dev, NULL, cxlds->regs.ras);
>> }
>>
>> /* CXL spec rev3.0 8.2.4.16.1 */
>> @@ -701,7 +701,8 @@ static void header_log_copy(void __iomem *ras_base, u32 *log)
>> * Log the state of the RAS status registers and prepare them to log the
>> * next error status. Return 1 if reset needed.
>> */
>> -static pci_ers_result_t __cxl_handle_ras(struct device *dev, void __iomem *ras_base)
>> +static pci_ers_result_t __cxl_handle_ras(struct device *cxl_dev, struct device *pcie_dev,
>> + void __iomem *ras_base)
>> {
>> u32 hl[CXL_HEADERLOG_SIZE_U32];
>> void __iomem *addr;
>> @@ -709,7 +710,7 @@ static pci_ers_result_t __cxl_handle_ras(struct device *dev, void __iomem *ras_b
>> u32 fe;
>>
>> if (!ras_base) {
>> - dev_warn_once(dev, "CXL RAS register block is not mapped");
>> + dev_warn_once(cxl_dev, "CXL RAS register block is not mapped");
>> return PCI_ERS_RESULT_NONE;
>> }
>>
>> @@ -730,10 +731,10 @@ static pci_ers_result_t __cxl_handle_ras(struct device *dev, void __iomem *ras_b
>> }
>>
>> header_log_copy(ras_base, hl);
>> - if (is_cxl_memdev(dev))
>> - trace_cxl_aer_uncorrectable_error(to_cxl_memdev(dev), status, fe, hl);
>> - else if (is_cxl_port(dev))
>> - trace_cxl_port_aer_uncorrectable_error(dev, status, fe, hl);
>> + if (is_cxl_memdev(cxl_dev))
>> + trace_cxl_aer_uncorrectable_error(to_cxl_memdev(cxl_dev), status, fe, hl);
>> + else if (is_cxl_port(cxl_dev))
>> + trace_cxl_port_aer_uncorrectable_error(cxl_dev, pcie_dev, status, fe, hl);
>>
>> writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);
>>
>> @@ -742,7 +743,7 @@ static pci_ers_result_t __cxl_handle_ras(struct device *dev, void __iomem *ras_b
>>
>> static bool cxl_handle_endpoint_ras(struct cxl_dev_state *cxlds)
>> {
>> - return __cxl_handle_ras(&cxlds->cxlmd->dev, cxlds->regs.ras);
>> + return __cxl_handle_ras(&cxlds->cxlmd->dev, NULL, cxlds->regs.ras);
>> }
>>
>> #ifdef CONFIG_PCIEAER_CXL
>> @@ -814,7 +815,7 @@ static void __iomem *cxl_pci_port_ras(struct pci_dev *pdev, struct device **dev)
>> struct cxl_dport *dport = NULL;
>>
>> port = find_cxl_port(&pdev->dev, &dport);
>> - if (!port) {
>> + if (!port || !is_cxl_port(&port->dev)) {
>> pci_err(pdev, "Failed to find root/dport in CXL topology\n");
>> return NULL;
>> }
>> @@ -848,7 +849,7 @@ static void cxl_port_cor_error_detected(struct pci_dev *pdev)
>> struct device *dev;
>> void __iomem *ras_base = cxl_pci_port_ras(pdev, &dev);
>>
>> - __cxl_handle_cor_ras(dev, ras_base);
>> + __cxl_handle_cor_ras(dev, &pdev->dev, ras_base);
>> }
>>
>> static pci_ers_result_t cxl_port_error_detected(struct pci_dev *pdev)
>> @@ -856,7 +857,7 @@ static pci_ers_result_t cxl_port_error_detected(struct pci_dev *pdev)
>> struct device *dev;
>> void __iomem *ras_base = cxl_pci_port_ras(pdev, &dev);
>>
>> - return __cxl_handle_ras(dev, ras_base);
>> + return __cxl_handle_ras(dev, &pdev->dev, ras_base);
>> }
>>
>> void cxl_uport_init_ras_reporting(struct cxl_port *port)
>> @@ -909,13 +910,13 @@ EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, "CXL");
>> static void cxl_handle_rdport_cor_ras(struct cxl_dev_state *cxlds,
>> struct cxl_dport *dport)
>> {
>> - return __cxl_handle_cor_ras(&cxlds->cxlmd->dev, dport->regs.ras);
>> + return __cxl_handle_cor_ras(&cxlds->cxlmd->dev, NULL, dport->regs.ras);
>> }
>>
>> static bool cxl_handle_rdport_ras(struct cxl_dev_state *cxlds,
>> struct cxl_dport *dport)
>> {
>> - return __cxl_handle_ras(&cxlds->cxlmd->dev, dport->regs.ras);
>> + return __cxl_handle_ras(&cxlds->cxlmd->dev, NULL, dport->regs.ras);
>> }
>>
>> /*
>> diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
>> index b536233ac210..a74803f4aa22 100644
>> --- a/drivers/cxl/core/trace.h
>> +++ b/drivers/cxl/core/trace.h
>> @@ -49,18 +49,22 @@
>> )
>>
>> TRACE_EVENT(cxl_port_aer_uncorrectable_error,
>> - TP_PROTO(struct device *dev, u32 status, u32 fe, u32 *hl),
>> - TP_ARGS(dev, status, fe, hl),
>> + TP_PROTO(struct device *cxl_dev, struct device *pcie_dev, u32 status, u32 fe, u32 *hl),
>> + TP_ARGS(cxl_dev, pcie_dev, status, fe, hl),
>> TP_STRUCT__entry(
>> - __string(devname, dev_name(dev))
>> - __string(parent, dev_name(dev->parent))
>> + __string(cxl_name, dev_name(cxl_dev))
>> + __string(cxl_parent_name, dev_name(cxl_dev->parent))
>> + __string(pcie_name, dev_name(pcie_dev))
>> + __string(pcie_parent_name, dev_name(pcie_dev->parent))
>> __field(u32, status)
>> __field(u32, first_error)
>> __array(u32, header_log, CXL_HEADERLOG_SIZE_U32)
>> ),
>> TP_fast_assign(
>> - __assign_str(devname);
>> - __assign_str(parent);
>> + __assign_str(cxl_name);
>> + __assign_str(cxl_parent_name);
>> + __assign_str(pcie_name);
>> + __assign_str(pcie_parent_name);
>> __entry->status = status;
>> __entry->first_error = fe;
>> /*
>> @@ -69,8 +73,9 @@ TRACE_EVENT(cxl_port_aer_uncorrectable_error,
>> */
>> memcpy(__entry->header_log, hl, CXL_HEADERLOG_SIZE);
>> ),
>> - TP_printk("device=%s parent=%s status: '%s' first_error: '%s'",
>> - __get_str(devname), __get_str(parent),
>> + TP_printk("device=%s (%s) parent=%s (%s) status: '%s' first_error: '%s'",
>> + __get_str(cxl_name), __get_str(pcie_name),
>> + __get_str(cxl_parent_name), __get_str(pcie_parent_name),
>> show_uc_errs(__entry->status),
>> show_uc_errs(__entry->first_error)
>> )
>> @@ -125,20 +130,25 @@ TRACE_EVENT(cxl_aer_uncorrectable_error,
>> )
>>
>> TRACE_EVENT(cxl_port_aer_correctable_error,
>> - TP_PROTO(struct device *dev, u32 status),
>> - TP_ARGS(dev, status),
>> + TP_PROTO(struct device *cxl_dev, struct device *pcie_dev, u32 status),
>> + TP_ARGS(cxl_dev, pcie_dev, status),
>> TP_STRUCT__entry(
>> - __string(devname, dev_name(dev))
>> - __string(parent, dev_name(dev->parent))
>> + __string(cxl_name, dev_name(cxl_dev))
>> + __string(cxl_parent_name, dev_name(cxl_dev->parent))
>> + __string(pcie_name, dev_name(pcie_dev))
>> + __string(pcie_parent_name, dev_name(pcie_dev->parent))
>> __field(u32, status)
>> ),
>> TP_fast_assign(
>> - __assign_str(devname);
>> - __assign_str(parent);
>> + __assign_str(cxl_name);
>> + __assign_str(cxl_parent_name);
>> + __assign_str(pcie_name);
>> + __assign_str(pcie_parent_name);
>> __entry->status = status;
>> ),
>> - TP_printk("device=%s parent=%s status='%s'",
>> - __get_str(devname), __get_str(parent),
>> + TP_printk("device=%s (%s) parent=%s (%s) status='%s'",
>> + __get_str(cxl_name), __get_str(pcie_name),
>> + __get_str(cxl_parent_name), __get_str(pcie_parent_name),
>> show_ce_errs(__entry->status)
>> )
>> );
