Re: [PATCH v10 03/17] PCI/AER: Report CXL or PCIe bus error type in trace logging
From: Dave Jiang
Date: Tue Jul 01 2025 - 17:27:40 EST
On 6/26/25 3:42 PM, Terry Bowman wrote:
> 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 the 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@xxxxxxx>
> Reviewed-by: Ira Weiny <ira.weiny@xxxxxxxxx>
Reviewed-by: Dave Jiang <dave.jiang@xxxxxxxxx>
> ---
> drivers/pci/pci.h | 6 ++++++
> drivers/pci/pcie/aer.c | 21 +++++++++++++++------
> include/ras/ras_event.h | 9 ++++++---
> 3 files changed, 27 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
> index 12215ee72afb..a0d1e59b5666 100644
> --- a/drivers/pci/pci.h
> +++ b/drivers/pci/pci.h
> @@ -608,6 +608,7 @@ struct aer_err_info {
> int ratelimit_print[AER_MAX_MULTI_ERR_DEVICES];
> int error_dev_num;
> const char *level; /* printk level */
> + bool is_cxl;
>
> unsigned int id:16;
>
> @@ -628,6 +629,11 @@ 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 70ac66188367..a2df9456595a 100644
> --- a/drivers/pci/pcie/aer.c
> +++ b/drivers/pci/pcie/aer.c
> @@ -837,6 +837,7 @@ 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;
> @@ -845,23 +846,23 @@ void aer_print_error(struct aer_err_info *info, int i)
> id = pci_dev_id(dev);
>
> pci_dev_aer_stats_incr(dev, info);
> - trace_aer_event(pci_name(dev), (info->status & ~info->mask),
> + trace_aer_event(pci_name(dev), bus_type, (info->status & ~info->mask),
> info->severity, info->tlp_header_valid, &info->tlp);
>
> 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",
> @@ -895,6 +896,7 @@ 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 = {
> @@ -915,9 +917,12 @@ 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),
> + trace_aer_event(pci_name(dev), bus_type, (status & ~mask),
> aer_severity, tlp_header_valid, &aer->header_log);
>
> if (!aer_ratelimit(dev, info.severity))
> @@ -939,6 +944,9 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
> if (tlp_header_valid)
> pcie_print_tlp_log(dev, &aer->header_log, info.level,
> dev_fmt(" "));
> +
> + trace_aer_event(dev_name(&dev->dev), bus_type, (status & ~mask),
> + aer_severity, tlp_header_valid, &aer->header_log);
> }
> EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL");
>
> @@ -1371,6 +1379,7 @@ 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 14c9f943d53f..080829d59c36 100644
> --- a/include/ras/ras_event.h
> +++ b/include/ras/ras_event.h
> @@ -297,15 +297,17 @@ TRACE_EVENT(non_standard_event,
>
> TRACE_EVENT(aer_event,
> TP_PROTO(const char *dev_name,
> + const char *bus_type,
> const u32 status,
> const u8 severity,
> const u8 tlp_header_valid,
> struct pcie_tlp_log *tlp),
>
> - TP_ARGS(dev_name, status, severity, tlp_header_valid, tlp),
> + TP_ARGS(dev_name, bus_type, status, severity, tlp_header_valid, tlp),
>
> TP_STRUCT__entry(
> __string( dev_name, dev_name )
> + __string( bus_type, bus_type )
> __field( u32, status )
> __field( u8, severity )
> __field( u8, tlp_header_valid)
> @@ -314,6 +316,7 @@ TRACE_EVENT(aer_event,
>
> TP_fast_assign(
> __assign_str(dev_name);
> + __assign_str(bus_type);
> __entry->status = status;
> __entry->severity = severity;
> __entry->tlp_header_valid = tlp_header_valid;
> @@ -325,8 +328,8 @@ 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",