| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <c4f88c14-293a-4fd7-8a65-03ee3cfec93e@amd.com>
Date: Wed, 4 Jun 2025 16:30:00 -0500
From: "Bowman, Terry" <terry.bowman@....com>
To: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@...ux.intel.com>,
PradeepVineshReddy.Kodamati@....com, dave@...olabs.net,
jonathan.cameron@...wei.com, dave.jiang@...el.com,
alison.schofield@...el.com, vishal.l.verma@...el.com, ira.weiny@...el.com,
dan.j.williams@...el.com, bhelgaas@...gle.com, bp@...en8.de,
ming.li@...omail.com, shiju.jose@...wei.com, dan.carpenter@...aro.org,
Smita.KoralahalliChannabasappa@....com, kobayashi.da-06@...itsu.com,
yanfei.xu@...el.com, rrichter@....com, peterz@...radead.org, colyli@...e.de,
uaisheng.ye@...el.com, fabio.m.de.francesco@...ux.intel.com,
ilpo.jarvinen@...ux.intel.com, yazen.ghannam@....com,
linux-cxl@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-pci@...r.kernel.org
Subject: Re: [PATCH v9 02/16] PCI/AER: Report CXL or PCIe bus error type in
trace logging
On 6/4/2025 2:24 PM, Sathyanarayanan Kuppuswamy wrote:
>
> On 6/4/25 7:32 AM, Bowman, Terry wrote:
>>
>> On 6/3/2025 5:02 PM, Sathyanarayanan Kuppuswamy wrote:
>>> On 6/3/25 10:22 AM, 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@....com>
>>>> Reviewed-by: Ira Weiny <ira.weiny@...el.com>
>>>> ---
>>>> drivers/pci/pci.h | 6 ++++++
>>>> drivers/pci/pcie/aer.c | 18 ++++++++++++------
>>>> include/ras/ras_event.h | 9 ++++++---
>>>> 3 files changed, 24 insertions(+), 9 deletions(-)
>>>>
>>>> diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
>>>> index b81e99cd4b62..d6296500b004 100644
>>>> --- a/drivers/pci/pci.h
>>>> +++ b/drivers/pci/pci.h
>>>> @@ -588,6 +588,7 @@ static inline bool pci_dev_test_and_set_removed(struct pci_dev *dev)
>>>> struct aer_err_info {
>>>> struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
>>>> int error_dev_num;
>>>> + bool is_cxl;
>>> Do you really need this member ? Why not just use pcie_is_cxl() in aer_err_bus()?
>> This was added per Dan's request instead of using pcie_is_cxl().[1]
>>
>> [1] https://lore.kernel.org/linux-cxl/67abe1903a8ed_2d1e2942f@dwillia2-xfh.jf.intel.com.notmuch/
>>
>> -Terry
>
> It looks like it is added to accommodate some future use cases. May be add some info about it in the aer_err_info struct. Just looking at the code, that member value mirrors pci_dev->is_cxl and where ever you read info->cxl, you can also read the value from pci_dev->is_cxl.
Right. pci_dev::is_cxl is currently only updated at device creation but could be tied
to alternate protocol training and link status changes.
Terry
>>>>
>>>> unsigned int id:16;
>>>>
>>>> @@ -604,6 +605,11 @@ struct aer_err_info {
>>>> struct pcie_tlp_log tlp; /* TLP Header */
>>>> };
>>>>
>>>> +static inline const char *aer_err_bus(struct aer_err_info *info)
>>>> +{
>>>> + return info->is_cxl ? "CXL" : "PCIe";
>>>> +}
>>>> +
>>>> int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info);
>>>> void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
>>>>
>>>> diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
>>>> index a1cf8c7ef628..adb4b1123b9b 100644
>>>> --- a/drivers/pci/pcie/aer.c
>>>> +++ b/drivers/pci/pcie/aer.c
>>>> @@ -698,13 +698,14 @@ static void __aer_print_error(struct pci_dev *dev,
>>>>
>>>> void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>>>> {
>>>> + const char *bus_type = aer_err_bus(info);
>>>> int layer, agent;
>>>> int id = pci_dev_id(dev);
>>>> const char *level;
>>>>
>>>> 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;
>>>> }
>>>>
>>>> @@ -713,8 +714,8 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>>>>
>>>> level = (info->severity == AER_CORRECTABLE) ? KERN_WARNING : KERN_ERR;
>>>>
>>>> - 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",
>>>> @@ -729,7 +730,7 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>>>> if (info->id && info->error_dev_num > 1 && info->id == id)
>>>> pci_err(dev, " Error of this Agent is reported first\n");
>>>>
>>>> - trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
>>>> + trace_aer_event(dev_name(&dev->dev), bus_type, (info->status & ~info->mask),
>>>> info->severity, info->tlp_header_valid, &info->tlp);
>>>> }
>>>>
>>>> @@ -763,6 +764,7 @@ 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;
>>>> @@ -784,6 +786,9 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
>>>> info.status = status;
>>>> info.mask = mask;
>>>> info.first_error = PCI_ERR_CAP_FEP(aer->cap_control);
>>>> + info.is_cxl = pcie_is_cxl(dev);
>>>> +
>>>> + bus_type = aer_err_bus(&info);
>>>>
>>>> pci_err(dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", status, mask);
>>>> __aer_print_error(dev, &info);
>>>> @@ -797,7 +802,7 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
>>>> if (tlp_header_valid)
>>>> pcie_print_tlp_log(dev, &aer->header_log, dev_fmt(" "));
>>>>
>>>> - trace_aer_event(dev_name(&dev->dev), (status & ~mask),
>>>> + 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");
>>>> @@ -1215,6 +1220,7 @@ int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
>>>> /* 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",
>>
Powered by blists - more mailing lists