Re: [PATCH v8 5/6] drm/xe: Suppress Surprise Link Down on device

[Raag Jadav <raag.jadav@intel.com>]

On Fri, Jun 12, 2026 at 01:37:28PM +0530, Mallesh Koujalagi wrote:
> PUNIT errors can only be recovered using a power-cycle. Xe KMD
> sends a uevent to notify userspace to trigger a power cycle.
> On platforms where link drop caused by powering the device off and
> back on is reported by hardware as a Surprise Link Down (SLD), which
> AER then escalates as an Uncorrectable Fatal Error. That error fires
> before the device finishes coming back up and defeats the
> very recovery we are attempting.
> 
> To keep the expected, recovery-induced link drop from being raised as
> a fatal AER event, mask the Surprise Link Down bit
> (PCI_ERR_UNC_SURPDN) in the upstream port's AER Uncorrectable Error
> Mask register before punit_error_handler() requests the cold reset.
> 
> Signed-off-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
> ---
> v6:
> - Expand commit message to explain why SUR_DN is masked. (Raag/Riana)
> - Check Slot Implemented bit before reading Slot Capabilities, per
>   PCIe spec. (Riana)
> - Add debug log.
> 
> v7:
> - Handle surprise link down event properly. (Aravind/Riana)
> - Update commit message. (Riana)
> - Correct log message.
> 
> v8:
> - Use find_usp_dev() in punit_error_handler() function.
> ---
>  drivers/gpu/drm/xe/xe_ras.c | 65 ++++++++++++++++++++++++++++---------
>  1 file changed, 49 insertions(+), 16 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
> index 93a56a0269f1..15c2fa0d323a 100644
> --- a/drivers/gpu/drm/xe/xe_ras.c
> +++ b/drivers/gpu/drm/xe/xe_ras.c
> @@ -209,8 +209,57 @@ static enum xe_ras_recovery_action handle_core_compute_errors(struct xe_ras_erro
>  	return XE_RAS_RECOVERY_ACTION_RECOVERED;
>  }
>  
> +static struct pci_dev *find_usp_dev(struct pci_dev *pdev)
> +{
> +	struct pci_dev *vsp;
> +
> +	/*
> +	 * Device Hierarchy:
> +	 *
> +	 * Upstream Switch Port (USP) --> Virtual Switch Port (VSP) --> SGunit (GPU endpoint)
> +	 */
> +	vsp = pci_upstream_bridge(pdev);
> +	if (!vsp)
> +		return NULL;
> +
> +	return pci_upstream_bridge(vsp);
> +}

Unneeded churn, please make sure the function is already at the top in
the original series.

> +#ifdef CONFIG_PCIEAER
> +static void pcie_suppress_surprise_link_down(struct pci_dev *usp)
> +{
> +	u32 aer_uncorr_mask;
> +	u16 aer_cap;
> +
> +	aer_cap = usp->aer_cap;
> +	if (!aer_cap) {
> +		dev_dbg(&usp->dev,
> +			"AER capability not present\n");
> +		return;
> +	}
> +
> +	pci_read_config_dword(usp, aer_cap + PCI_ERR_UNCOR_MASK, &aer_uncorr_mask);
> +	aer_uncorr_mask |= PCI_ERR_UNC_SURPDN;
> +	pci_write_config_dword(usp, aer_cap + PCI_ERR_UNCOR_MASK, aer_uncorr_mask);
> +	dev_dbg(&usp->dev, "Surprise Link Down masked for cold reset\n");

What about when we come back on after successful recovery? Do we need to
unmask it?

Raag

> +}
> +#endif /* CONFIG_PCIEAER */
> +
>  static void punit_error_handler(struct xe_device *xe)
>  {
> +#ifdef CONFIG_PCIEAER
> +	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
> +	struct pci_dev *usp;
> +
> +	/*
> +	 * Cold reset power-cycles the slot, dropping the PCIe link. The
> +	 * slot triggers a spurious Surprise Link Down AER event on the USP.
> +	 */
> +	usp = find_usp_dev(pdev);
> +
> +	if (usp)
> +		pcie_suppress_surprise_link_down(usp);
> +#endif
>  	xe_device_set_wedged_method(xe, DRM_WEDGE_RECOVERY_COLD_RESET);
>  	xe_device_declare_wedged(xe);
>  }
> @@ -503,22 +552,6 @@ enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe)
>  	return XE_RAS_RECOVERY_ACTION_RESET;
>  }
>  
> -static struct pci_dev *find_usp_dev(struct pci_dev *pdev)
> -{
> -	struct pci_dev *vsp;
> -
> -	/*
> -	 * Device Hierarchy:
> -	 *
> -	 * Upstream Switch Port (USP) --> Virtual Switch Port (VSP) --> SGunit (GPU endpoint)
> -	 */
> -	vsp = pci_upstream_bridge(pdev);
> -	if (!vsp)
> -		return NULL;
> -
> -	return pci_upstream_bridge(vsp);
> -}
> -
>  static void aer_unmask_and_downgrade_internal_error(struct xe_device *xe)
>  {
>  	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
> -- 
> 2.34.1
>