Re: [PATCH] PCI/DPC: Fix print AER status in DPC event handling

Re: [PATCH] PCI/DPC: Fix print AER status in DPC event handling

[Dongdong Liu]

Ping :)

在 2019/1/3 15:38, Dongdong Liu 写道:
> Current info->severity have not assigned a value before calling
> aer_get_device_error_info() and aer_get_device_error_info(),
> Fix the bug to get the severity by reading the port's AER status, mask
> and severity registers. At the same time, add code to clear the port's
> fatal errors.
>
> Fixes: 8aefa9b0d910 ("PCI/DPC: Print AER status in DPC event handling")
> Signed-off-by: Dongdong Liu <liudongdong3@huawei.com>
> Cc: stable@vger.kernel.org # 4.19+
> ---
>  drivers/pci/pcie/dpc.c | 27 ++++++++++++++++++++++++++-
>  1 file changed, 26 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
> index e435d12..7b77754 100644
> --- a/drivers/pci/pcie/dpc.c
> +++ b/drivers/pci/pcie/dpc.c
> @@ -202,6 +202,28 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
>  	pci_write_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_STATUS, status);
>  }
>
> +static int dpc_get_aer_uncorrect_severity(struct pci_dev *dev,
> +					  struct aer_err_info *info)
> +{
> +	int pos = dev->aer_cap;
> +	u32 status, mask, sev;
> +
> +	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
> +	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, &mask);
> +	status &= ~mask;
> +	if (!status)
> +		return 0;
> +
> +	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev);
> +	status &= sev;
> +	if (status)
> +		info->severity = AER_FATAL;
> +	else
> +		info->severity = AER_NONFATAL;
> +
> +	return 1;
> +}
> +
>  static irqreturn_t dpc_handler(int irq, void *context)
>  {
>  	struct aer_err_info info;
> @@ -229,9 +251,12 @@ static irqreturn_t dpc_handler(int irq, void *context)
>  	/* show RP PIO error detail information */
>  	if (dpc->rp_extensions && reason == 3 && ext_reason == 0)
>  		dpc_process_rp_pio_error(dpc);
> -	else if (reason == 0 && aer_get_device_error_info(pdev, &info)) {
> +	else if (reason == 0 &&
> +		 dpc_get_aer_uncorrect_severity(pdev, &info) &&
> +		 aer_get_device_error_info(pdev, &info)) {
>  		aer_print_error(pdev, &info);
>  		pci_cleanup_aer_uncorrect_error_status(pdev);
> +		pci_aer_clear_fatal_status(pdev);
>  	}
>
>  	/* We configure DPC so it only triggers on ERR_FATAL */
>