Re: [PATCH v16 09/10] cxl: Remove Endpoint AER correctable handler

[Dave Jiang <dave.jiang@intel.com>]

On 3/2/26 1:36 PM, Terry Bowman wrote:
> CXL drivers dont require a correctable PCI AER handler. Correctable AER
> errors reported by CXL devices are logged and cleared in the AER driver.
> This makes the correctable AER handler callback in the CXL driver
> unnecessary.
> 
> Remove cxl_cor_error_detected() and drop the .cor_error_detected callback
> from the CXL PCI error handlers.
> 
> This consolidates correctable error reporting under the CXL RAS infrastructure
> and avoids redundant or conflicting logging with the AER driver.
> 
> Signed-off-by: Terry Bowman <terry.bowman@amd.com>

Reviewed-by: Dave Jiang <dave.jiang@intel.com>


> 
> ---
> 
> Changes in v15->v16:
> - None
> 
> Changes in v14->v15:
> - Remove cxl_pci_cor_error_detected(). Is not needed. AER is logged
>   in the AER driver. (Dan)
> - Update commit message (Terry)
> 
> Changes in v13->v14:
> - New commit
> - Change cxl_cor_error_detected() parameter to &pdev->dev device from
>   memdev device. (Terry)
> - Updated commit message (Terry)
> ---
>  drivers/cxl/core/ras.c | 23 -----------------------
>  drivers/cxl/cxlpci.h   |  2 --
>  drivers/cxl/pci.c      |  1 -
>  3 files changed, 26 deletions(-)
> 
> diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
> index 884e40c66638..d6112b812c82 100644
> --- a/drivers/cxl/core/ras.c
> +++ b/drivers/cxl/core/ras.c
> @@ -370,29 +370,6 @@ cxl_handle_ras(struct device *dev, u64 serial, void __iomem *ras_base)
>  	return PCI_ERS_RESULT_PANIC;
>  }
>  
> -void cxl_cor_error_detected(struct pci_dev *pdev)
> -{
> -	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
> -	struct cxl_memdev *cxlmd = cxlds->cxlmd;
> -	struct device *dev = &cxlds->cxlmd->dev;
> -
> -	scoped_guard(device, dev) {
> -		if (!dev->driver) {
> -			dev_warn(&pdev->dev,
> -				 "%s: memdev disabled, abort error handling\n",
> -				 dev_name(dev));
> -			return;
> -		}
> -
> -		if (cxlds->rcd)
> -			cxl_handle_rdport_errors(pdev);
> -
> -		cxl_handle_cor_ras(&cxlds->cxlmd->dev, cxlds->serial,
> -				   cxlmd->endpoint->regs.ras);
> -	}
> -}
> -EXPORT_SYMBOL_NS_GPL(cxl_cor_error_detected, "CXL");
> -
>  static bool cxl_uncor_aer_present(struct pci_dev *pdev)
>  {
>  	struct aer_capability_regs aer_regs;
> diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h
> index 86029d96d6bb..184a95e96ea9 100644
> --- a/drivers/cxl/cxlpci.h
> +++ b/drivers/cxl/cxlpci.h
> @@ -78,13 +78,11 @@ struct cxl_dev_state;
>  void read_cdat_data(struct cxl_port *port);
>  
>  #ifdef CONFIG_CXL_RAS
> -void cxl_cor_error_detected(struct pci_dev *pdev);
>  void devm_cxl_dport_rch_ras_setup(struct cxl_dport *dport);
>  pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
>  					pci_channel_state_t error);
>  void devm_cxl_port_ras_setup(struct cxl_port *port);
>  #else
> -static inline void cxl_cor_error_detected(struct pci_dev *pdev) { }
>  static inline pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
>  						      pci_channel_state_t state)
>  {
> diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
> index b57f4727af53..77a2ee57222b 100644
> --- a/drivers/cxl/pci.c
> +++ b/drivers/cxl/pci.c
> @@ -1055,7 +1055,6 @@ static const struct pci_error_handlers pci_error_handlers = {
>  	.error_detected	= cxl_pci_error_detected,
>  	.slot_reset	= cxl_slot_reset,
>  	.resume		= cxl_error_resume,
> -	.cor_error_detected	= cxl_cor_error_detected,
>  	.reset_done	= cxl_reset_done,
>  };
>