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@xxxxxxx>
> ---
> v2:
> Removed pr_warn for serial number.
> p_err -> rec/p_rec.
> ---
> drivers/acpi/apei/ghes.c | 14 ++++++++++++++
> drivers/cxl/core/pci.c | 24 ++++++++++++++++++++++++
> drivers/cxl/cxlpci.h | 3 +++
> drivers/cxl/pci.c | 20 ++++++++++++++++++--
> include/cxl/event.h | 1 +
> 5 files changed, 60 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index 9dcf0f78458f..5082885e1f2c 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_rec))
> 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 5b46bc46aaa9..39ef24c8991f 100644
> --- a/drivers/cxl/core/pci.c
> +++ b/drivers/cxl/core/pci.c
> @@ -650,6 +650,30 @@ 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 *rec)
> +{
> + u32 status, fe;
> +
> + if (rec->severity == CXL_AER_CORRECTABLE) {
> + status = rec->cxl_ras.cor_status & ~rec->cxl_ras.cor_mask;
> +
> + trace_cxl_aer_correctable_error(cxlds->cxlmd, status);
> + } else {
> + status = rec->cxl_ras.uncor_status & ~rec->cxl_ras.uncor_mask;
> +
> + if (hweight32(status) > 1)
> + fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
> + rec->cxl_ras.cap_control));
> + else
> + fe = status;
> +
> + trace_cxl_aer_uncorrectable_error(cxlds->cxlmd, status, fe,
> + rec->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 4da07727ab9c..8acd8f2c39c9 100644
> --- a/drivers/cxl/cxlpci.h
> +++ b/drivers/cxl/cxlpci.h
> @@ -129,4 +129,7 @@ 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 *rec);
> #endif /* __CXL_PCI_H__ */
> diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
> index 915102f5113f..0a29321921a0 100644
> --- a/drivers/cxl/pci.c
> +++ b/drivers/cxl/pci.c
> @@ -1064,12 +1064,28 @@ 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 *rec)
> +{
> + struct cxl_dev_state *cxlds;
> +
> + cxlds = get_cxl_devstate(rec->segment, rec->bus,
> + rec->device, rec->function);
As mentioned in 2/4 I don't think this is going to work correctly.
> + if (!cxlds)
> + return;
> +
> + cxl_trace_prot_err(cxlds, rec);
> +}
> +
> static void cxl_cper_work_fn(struct work_struct *work)
> {
> struct cxl_cper_work_data wd;
>
> - while (cxl_cper_kfifo_get(&wd))
> - cxl_handle_cper_event(wd.event_type, &wd.rec);
> + while (cxl_cper_kfifo_get(&wd)) {
> + if (wd.event_type == CXL_CPER_EVENT_PROT_ERR)
> + cxl_handle_prot_err(&wd.p_rec);
> + else
> + cxl_handle_cper_event(wd.event_type, &wd.rec);
Why does this need to change?
Have cxl_handle_cper_event() decode the BDF as it does now and call
cxl_handle_prot_err() there? I think you could drop patch 2/4 entirely
and not have to duplicate the logic.
Ira
> + }
> }
> static DECLARE_WORK(cxl_cper_work, cxl_cper_work_fn);
>
> diff --git a/include/cxl/event.h b/include/cxl/event.h
> index 5b316150556a..d854d8c435db 100644
> --- a/include/cxl/event.h
> +++ b/include/cxl/event.h
> @@ -115,6 +115,7 @@ struct cxl_event_record_raw {
> } __packed;
>
> enum cxl_event_type {
> + CXL_CPER_EVENT_PROT_ERR,
> CXL_CPER_EVENT_GENERIC,
> CXL_CPER_EVENT_GEN_MEDIA,
> CXL_CPER_EVENT_DRAM,
> --
> 2.17.1
>
