Re: [PATCH 3/4] acpi/ghes, cxl/pci: Trace FW-First CXL Protocol Errors

[Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>]

On 5/22/2024 11:05 AM, Dave Jiang wrote:
> 
> 
> On 5/22/24 8:08 AM, Smita Koralahalli wrote:
>> When PCIe AER is in FW-First, OS should process CXL Protocol errors from
>> CPER records.
>>
>> Reuse the existing work queue cxl_cper_work registered with GHES to notify
>> the CXL subsystem on a Protocol error.
>>
>> The defined trace events cxl_aer_uncorrectable_error and
>> cxl_aer_correctable_error currently trace native CXL AER errors. Reuse
>> them to trace FW-First Protocol Errors.
>>
>> Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
>> ---
>>   drivers/acpi/apei/ghes.c  | 14 ++++++++++++++
>>   drivers/cxl/core/pci.c    | 24 ++++++++++++++++++++++++
>>   drivers/cxl/cxlpci.h      |  3 +++
>>   drivers/cxl/pci.c         | 34 ++++++++++++++++++++++++++++++++--
>>   include/linux/cxl-event.h |  1 +
>>   5 files changed, 74 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
>> index 1a58032770ee..a31bd91e9475 100644
>> --- a/drivers/acpi/apei/ghes.c
>> +++ b/drivers/acpi/apei/ghes.c
>> @@ -723,6 +723,20 @@ static void cxl_cper_handle_prot_err(struct acpi_hest_generic_data *gdata)
>>   
>>   	if (cxl_cper_handle_prot_err_info(gdata, &wd.p_err))
>>   		return;
>> +
>> +	guard(spinlock_irqsave)(&cxl_cper_work_lock);
>> +
>> +	if (!cxl_cper_work)
>> +		return;
>> +
>> +	wd.event_type = CXL_CPER_EVENT_PROT_ERR;
>> +
>> +	if (!kfifo_put(&cxl_cper_fifo, wd)) {
>> +		pr_err_ratelimited("CXL CPER kfifo overflow\n");
>> +		return;
>> +	}
>> +
>> +	schedule_work(cxl_cper_work);
>>   }
>>   
>>   int cxl_cper_register_work(struct work_struct *work)
>> diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
>> index 0df09bd79408..ef9438cb1dd6 100644
>> --- a/drivers/cxl/core/pci.c
>> +++ b/drivers/cxl/core/pci.c
>> @@ -686,6 +686,30 @@ void read_cdat_data(struct cxl_port *port)
>>   }
>>   EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL);
>>   
>> +void cxl_trace_prot_err(struct cxl_dev_state *cxlds,
>> +			struct cxl_cper_prot_err *p_err)
>> +{
>> +	u32 status, fe;
>> +
>> +	if (p_err->severity == CXL_AER_CORRECTABLE) {
>> +		status = p_err->cxl_ras.cor_status & ~p_err->cxl_ras.cor_mask;
>> +
>> +		trace_cxl_aer_correctable_error(cxlds->cxlmd, status);
>> +	} else {
>> +		status = p_err->cxl_ras.uncor_status & ~p_err->cxl_ras.uncor_mask;
>> +
>> +		if (hweight32(status) > 1)
>> +			fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
>> +					   p_err->cxl_ras.cap_control));
>> +		else
>> +			fe = status;
>> +
>> +		trace_cxl_aer_uncorrectable_error(cxlds->cxlmd, status, fe,
>> +						  p_err->cxl_ras.header_log);
>> +	}
>> +}
>> +EXPORT_SYMBOL_NS_GPL(cxl_trace_prot_err, CXL);
>> +
>>   static void __cxl_handle_cor_ras(struct cxl_dev_state *cxlds,
>>   				 void __iomem *ras_base)
>>   {
>> diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h
>> index 93992a1c8eec..0ba3215786e1 100644
>> --- a/drivers/cxl/cxlpci.h
>> +++ b/drivers/cxl/cxlpci.h
>> @@ -130,4 +130,7 @@ void read_cdat_data(struct cxl_port *port);
>>   void cxl_cor_error_detected(struct pci_dev *pdev);
>>   pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
>>   				    pci_channel_state_t state);
>> +struct cxl_cper_prot_err;
>> +void cxl_trace_prot_err(struct cxl_dev_state *cxlds,
>> +			struct cxl_cper_prot_err *p_err);
>>   #endif /* __CXL_PCI_H__ */
>> diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
>> index 74876c9835e8..3e3c36983686 100644
>> --- a/drivers/cxl/pci.c
>> +++ b/drivers/cxl/pci.c
>> @@ -1011,12 +1011,42 @@ static void cxl_handle_cper_event(enum cxl_event_type ev_type,
>>   			       &uuid_null, &rec->event);
>>   }
>>   
>> +static void cxl_handle_prot_err(struct cxl_cper_prot_err *p_err)
>> +{
>> +	struct pci_dev *pdev __free(pci_dev_put) = NULL;
>> +	struct cxl_dev_state *cxlds;
>> +	unsigned int devfn;
>> +
>> +	devfn = PCI_DEVFN(p_err->device, p_err->function);
>> +	pdev = pci_get_domain_bus_and_slot(p_err->segment,
>> +					   p_err->bus, devfn);
>> +	if (!pdev)
>> +		return;
>> +
>> +	guard(device)(&pdev->dev);
>> +	if (pdev->driver != &cxl_pci_driver)
>> +		return;
>> +
>> +	cxlds = pci_get_drvdata(pdev);
>> +	if (!cxlds)
>> +		return;
>> +
>> +	if (((u64)p_err->upper_dw << 32 | p_err->lower_dw) != cxlds->serial)
>> +		pr_warn("CPER-reported device serial number does not match expected value\n");
> 
> Given that we are operating on a device, perhaps dev_warn(&pdev->dev, ...) may be better served.

Will fix.

Thanks,
Smita

[snip]