On 10/25/24 2:02 PM, Terry Bowman wrote:
> CXL.io provides PCIe like protocol error implementation, but CXL.io and
> PCIe have different handling requirements.
>
> The PCIe AER service driver may attempt recovering PCIe devices with
> uncorrectable errors while recovery is not used for CXL.io. Recovery is not
> used in the CXL.io recovery because of the potential for corruption on
> what can be system memory.
>
> Create pci_driver::cxl_err_handlers similar to pci_driver::error_handler.
> Create handlers for correctable and uncorrectable CXL.io error
> handling.
>
> The CXL error handlers will be used in future patches adding CXL PCIe
> port protocol error handling.
>
> Signed-off-by: Terry Bowman <terry.bowman@xxxxxxx>
Reviewed-by: Dave Jiang <dave.jiang@xxxxxxxxx>
> ---
> include/linux/pci.h | 9 +++++++++
> 1 file changed, 9 insertions(+)
>
> diff --git a/include/linux/pci.h b/include/linux/pci.h
> index 573b4c4c2be6..106ac83e3a7b 100644
> --- a/include/linux/pci.h
> +++ b/include/linux/pci.h
> @@ -886,6 +886,14 @@ struct pci_error_handlers {
> void (*cor_error_detected)(struct pci_dev *dev);
> };
>
> +/* CXL bus error event callbacks */
> +struct cxl_error_handlers {
> + /* CXL bus error detected on this device */
> + bool (*error_detected)(struct pci_dev *dev);
> +
> + /* Allow device driver to record more details of a correctable error */
> + void (*cor_error_detected)(struct pci_dev *dev);
> +};
>
> struct module;
>
> @@ -956,6 +964,7 @@ struct pci_driver {
> int (*sriov_set_msix_vec_count)(struct pci_dev *vf, int msix_vec_count); /* On PF */
> u32 (*sriov_get_vf_total_msix)(struct pci_dev *pf);
> const struct pci_error_handlers *err_handler;
> + const struct cxl_error_handlers *cxl_err_handler;
> const struct attribute_group **groups;
> const struct attribute_group **dev_groups;
> struct device_driver driver;
