Re: [PATCH v5 03/14] drm/xe/xe_pci_error: Implement PCI error recovery callbacks

["Mallesh, Koujalagi" <mallesh.koujalagi@intel.com>]

On 11-05-2026 10:59 pm, Riana Tauro wrote:
> Add error_detected, mmio_enabled, slot_reset and resume recovery callbacks
> to handle PCIe Advanced Error Reporting (AER) errors.
>
> For fatal errors, the device is wedged and becomes inaccessible. Return
> PCI_ERS_RESULT_SLOT_RESET from error_detected to request a Secondary
> Bus Reset (SBR).
>
> For non-fatal errors, return PCI_ERS_RESULT_CAN_RECOVER from
> error_detected to trigger the mmio_enabled callback. In this callback, the
> device is queried to determine the error cause and attempt recovery based
> on the error type.
>
> Once the secondary bus reset(SBR) is completed the slot_reset callback
> cleanly removes and reprobe the device to restore functionality.
>
> Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Matt Roper <matthew.d.roper@intel.com>
> Signed-off-by: Riana Tauro <riana.tauro@intel.com>
LGTM,
Reviewed-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
> ---
> v2: re-order linux headers
>      reword error messages
>      do not clear in_recovery after remove
>      return PCI_ERS_RESULT_DISCONNECT if probe fails (Michal)
>      only wedge device do not send uevent (Raag)
>      set recovery flag in error_detected and clear on resume
>      add default switch case (Mallesh)
>
> v3: do not set in_recovery for disconnect (Mallesh)
>      return if already wedged or in survivability mode
>
> v4: Add comment (Matthew)
>      Fix tab (Mallesh)
>
> v5: remove in_reset
>      disconnect if already in survivability mode or wedged
>      block I/O operations in slot reset (Raag)
>
> Note: The re-probe in this patch will be replaced by
> minimal re-initalization once below patch is merged
>   https://lore.kernel.org/intel-xe/f642453c-f657-41c7-a01b-5a0baf886cd3@intel.com/
>
> ---
>   drivers/gpu/drm/xe/Makefile       |   1 +
>   drivers/gpu/drm/xe/xe_pci.c       |   3 +
>   drivers/gpu/drm/xe/xe_pci_error.c | 115 ++++++++++++++++++++++++++++++
>   3 files changed, 119 insertions(+)
>   create mode 100644 drivers/gpu/drm/xe/xe_pci_error.c
>
> diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
> index 09661f079d03..091872771e98 100644
> --- a/drivers/gpu/drm/xe/Makefile
> +++ b/drivers/gpu/drm/xe/Makefile
> @@ -101,6 +101,7 @@ xe-y += xe_bb.o \
>   	xe_page_reclaim.o \
>   	xe_pat.o \
>   	xe_pci.o \
> +	xe_pci_error.o \
>   	xe_pci_rebar.o \
>   	xe_pcode.o \
>   	xe_pm.o \
> diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
> index d55e5af4f4b7..d970c27f5570 100644
> --- a/drivers/gpu/drm/xe/xe_pci.c
> +++ b/drivers/gpu/drm/xe/xe_pci.c
> @@ -1320,6 +1320,8 @@ static const struct dev_pm_ops xe_pm_ops = {
>   };
>   #endif
>   
> +extern const struct pci_error_handlers xe_pci_error_handlers;
> +
>   static struct pci_driver xe_pci_driver = {
>   	.name = DRIVER_NAME,
>   	.id_table = pciidlist,
> @@ -1327,6 +1329,7 @@ static struct pci_driver xe_pci_driver = {
>   	.remove = xe_pci_remove,
>   	.shutdown = xe_pci_shutdown,
>   	.sriov_configure = xe_pci_sriov_configure,
> +	.err_handler = &xe_pci_error_handlers,
>   #ifdef CONFIG_PM_SLEEP
>   	.driver.pm = &xe_pm_ops,
>   #endif
> diff --git a/drivers/gpu/drm/xe/xe_pci_error.c b/drivers/gpu/drm/xe/xe_pci_error.c
> new file mode 100644
> index 000000000000..42a821ca1a04
> --- /dev/null
> +++ b/drivers/gpu/drm/xe/xe_pci_error.c
> @@ -0,0 +1,115 @@
> +// SPDX-License-Identifier: MIT
> +/*
> + * Copyright © 2026 Intel Corporation
> + */
> +#include <linux/pci.h>
> +
> +#include <drm/drm_drv.h>
> +
> +#include "xe_device.h"
> +#include "xe_gt.h"
> +#include "xe_pci.h"
> +#include "xe_survivability_mode.h"
> +#include "xe_uc.h"
> +
> +static void xe_pci_error_handling(struct pci_dev *pdev)
> +{
> +	struct xe_device *xe = pdev_to_xe_device(pdev);
> +	struct xe_gt *gt;
> +	u8 id;
> +
> +	/*
> +	 * Wedge the device to prevent userspace access but don't send the event yet.
> +	 * Runtime PM ref is taken by PCI core for the duration of error handling.
> +	 */
> +	atomic_set(&xe->wedged.flag, 1);
> +
> +	for_each_gt(gt, xe, id)
> +		xe_gt_declare_wedged(gt);
> +
> +	pci_disable_device(pdev);
> +}
> +
> +static pci_ers_result_t xe_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
> +{
> +	struct xe_device *xe = pdev_to_xe_device(pdev);
> +
> +	dev_err(&pdev->dev, "Xe Pci error recovery: error detected state %d\n", state);
> +
> +	if (state == pci_channel_io_perm_failure)
> +		return PCI_ERS_RESULT_DISCONNECT;
> +
> +	/* If the device is already wedged or in survivability mode, do not attempt recovery */
> +	if (xe_survivability_mode_is_boot_enabled(xe) || xe_device_wedged(xe))
> +		return PCI_ERS_RESULT_DISCONNECT;
> +
> +	switch (state) {
> +	case pci_channel_io_normal:
> +		return PCI_ERS_RESULT_CAN_RECOVER;
> +	case pci_channel_io_frozen:
> +		xe_pci_error_handling(pdev);
> +		return PCI_ERS_RESULT_NEED_RESET;
> +	default:
> +		dev_err(&pdev->dev, "Unknown state %d\n", state);
> +		return PCI_ERS_RESULT_NEED_RESET;
> +	}
> +}
> +
> +static pci_ers_result_t xe_pci_error_mmio_enabled(struct pci_dev *pdev)
> +{
> +	dev_err(&pdev->dev, "Xe Pci error recovery: MMIO enabled\n");
> +
> +	return PCI_ERS_RESULT_NEED_RESET;
> +}
> +
> +static pci_ers_result_t xe_pci_error_slot_reset(struct pci_dev *pdev)
> +{
> +	const struct pci_device_id *ent = pci_match_id(pdev->driver->id_table, pdev);
> +	struct xe_device *xe;
> +
> +	dev_err(&pdev->dev, "Xe Pci error recovery: Slot reset\n");
> +
> +	pci_restore_state(pdev);
> +
> +	if (pci_enable_device(pdev)) {
> +		dev_err(&pdev->dev,
> +			"Cannot re-enable PCI device after reset\n");
> +		return PCI_ERS_RESULT_DISCONNECT;
> +	}
> +
> +	/*
> +	 * Secondary Bus Reset causes all VRAM state to be lost along with
> +	 * hardware state. As an initial step, re-probe the device to
> +	 * re-initialize the driver and hardware.
> +	 * TODO: optimize by re-initializing only the hardware state and re-creating
> +	 * kernel BOs.
> +	 */
> +	pdev->driver->remove(pdev);
> +
> +	if (pdev->driver->probe(pdev, ent))
> +		return PCI_ERS_RESULT_DISCONNECT;
> +
> +	xe = pdev_to_xe_device(pdev);
> +
> +	/* Wedge the device to prevent I/O operations till the resume callback */
> +	atomic_set(&xe->wedged.flag, 1);
> +
> +	return PCI_ERS_RESULT_RECOVERED;
> +}
> +
> +static void xe_pci_error_resume(struct pci_dev *pdev)
> +{
> +	struct xe_device *xe = pdev_to_xe_device(pdev);
> +
> +	dev_info(&pdev->dev, "Xe Pci error recovery: Recovered\n");
> +
> +	/* Resume I/O operations */
> +	atomic_set(&xe->wedged.flag, 0);
> +}
> +
> +const struct pci_error_handlers xe_pci_error_handlers = {
> +	.error_detected	= xe_pci_error_detected,
> +	.mmio_enabled	= xe_pci_error_mmio_enabled,
> +	.slot_reset	= xe_pci_error_slot_reset,
> +	.resume		= xe_pci_error_resume,
> +};