Re: [PATCH v7 2/5] PCI/DPC: Run recovery on device that detected the error

[Jonathan Cameron <jonathan.cameron@huawei.com>]

On Sat, 24 Jan 2026 15:45:54 +0800
Shuai Xue <xueshuai@linux.alibaba.com> wrote:

> The current implementation of pcie_do_recovery() assumes that the
> recovery process is executed for the device that detected the error.
> However, the DPC driver currently passes the error port that experienced
> the DPC event to pcie_do_recovery().
> 
> Use the SOURCE ID register to correctly identify the device that
> detected the error. When passing the error device, the
> pcie_do_recovery() will find the upstream bridge and walk bridges
> potentially AER affected. And subsequent commits will be able to
> accurately access AER status of the error device.
> 
> Should not observe any functional changes.
> 
> Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
> Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
> ---
>  drivers/pci/pci.h      |  2 +-
>  drivers/pci/pcie/dpc.c | 25 +++++++++++++++++++++----
>  drivers/pci/pcie/edr.c |  7 ++++---
>  3 files changed, 26 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
> index 0e67014aa001..58640e656897 100644
> --- a/drivers/pci/pci.h
> +++ b/drivers/pci/pci.h
> @@ -771,7 +771,7 @@ struct rcec_ea {
>  void pci_save_dpc_state(struct pci_dev *dev);
>  void pci_restore_dpc_state(struct pci_dev *dev);
>  void pci_dpc_init(struct pci_dev *pdev);
> -void dpc_process_error(struct pci_dev *pdev);
> +struct pci_dev *dpc_process_error(struct pci_dev *pdev);
>  pci_ers_result_t dpc_reset_link(struct pci_dev *pdev);
>  bool pci_dpc_recovered(struct pci_dev *pdev);
>  unsigned int dpc_tlp_log_len(struct pci_dev *dev);
> diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
> index bff29726c6a5..f6069f621683 100644
> --- a/drivers/pci/pcie/dpc.c
> +++ b/drivers/pci/pcie/dpc.c
> @@ -260,10 +260,20 @@ static int dpc_get_aer_uncorrect_severity(struct pci_dev *dev,
>  	return 1;
>  }
>  
> -void dpc_process_error(struct pci_dev *pdev)
> +/**
> + * dpc_process_error - handle the DPC error status
> + * @pdev: the port that experienced the containment event
> + *
> + * Return: the device that detected the error.
> + *
> + * NOTE: The device reference count is increased, the caller must decrement
> + * the reference count by calling pci_dev_put().
> + */
> +struct pci_dev *dpc_process_error(struct pci_dev *pdev)

Maybe it makes sense to carry the err_port naming for the pci_dev
in here as well?  Seems stronger than just relying on people
reading the documentation you've added.
 
>  {
>  	u16 cap = pdev->dpc_cap, status, source, reason, ext_reason;
>  	struct aer_err_info info = {};
> +	struct pci_dev *err_dev;
>  
>  	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
>  
> @@ -279,6 +289,7 @@ void dpc_process_error(struct pci_dev *pdev)
>  			pci_aer_clear_nonfatal_status(pdev);
>  			pci_aer_clear_fatal_status(pdev);
>  		}
> +		err_dev = pci_dev_get(pdev);
>  		break;
>  	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE:
>  	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE:
> @@ -290,6 +301,8 @@ void dpc_process_error(struct pci_dev *pdev)
>  				"ERR_FATAL" : "ERR_NONFATAL",
>  			 pci_domain_nr(pdev->bus), PCI_BUS_NUM(source),
>  			 PCI_SLOT(source), PCI_FUNC(source));
> +		err_dev = pci_get_domain_bus_and_slot(pci_domain_nr(pdev->bus),
> +					    PCI_BUS_NUM(source), source & 0xff);

Bunch of replication in her with the pci_warn(). Maybe some local variables?
Maybe even rebuild the final parameter from PCI_DEVFN(slot, func) just to make the
association with the print really obvious?

Is there any chance that this might return NULL?   Feels like maybe that's
only a possibility on a broken setup, but I'm not sure of all the wonderful
races around hotplug and DPC occurring before the OS has caught up.

>  		break;
>  	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT:
>  		ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT;
> @@ -304,8 +317,11 @@ void dpc_process_error(struct pci_dev *pdev)
>  		if (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO &&
>  		    pdev->dpc_rp_extensions)
>  			dpc_process_rp_pio_error(pdev);
> +		err_dev = pci_dev_get(pdev);
>  		break;
>  	}
> +
> +	return err_dev;
>  }

> diff --git a/drivers/pci/pcie/edr.c b/drivers/pci/pcie/edr.c
> index 521fca2f40cb..b6e9d652297e 100644
> --- a/drivers/pci/pcie/edr.c
> +++ b/drivers/pci/pcie/edr.c
> @@ -150,7 +150,7 @@ static int acpi_send_edr_status(struct pci_dev *pdev, struct pci_dev *edev,
>  
>  static void edr_handle_event(acpi_handle handle, u32 event, void *data)
>  {
> -	struct pci_dev *pdev = data, *err_port;
> +	struct pci_dev *pdev = data, *err_port, *err_dev;
>  	pci_ers_result_t estate = PCI_ERS_RESULT_DISCONNECT;
>  	u16 status;
>  
> @@ -190,7 +190,7 @@ static void edr_handle_event(acpi_handle handle, u32 event, void *data)
>  		goto send_ost;
>  	}
>  
> -	dpc_process_error(err_port);
> +	err_dev = dpc_process_error(err_port);
>  	pci_aer_raw_clear_status(err_port);
>  
>  	/*
> @@ -198,7 +198,8 @@ static void edr_handle_event(acpi_handle handle, u32 event, void *data)
>  	 * or ERR_NONFATAL, since the link is already down, use the FATAL
>  	 * error recovery path for both cases.
>  	 */
> -	estate = pcie_do_recovery(err_port, pci_channel_io_frozen, dpc_reset_link);
> +	estate = pcie_do_recovery(err_dev, pci_channel_io_frozen, dpc_reset_link);
> +	pci_dev_put(err_dev);
>  
>  send_ost:
>