From: Riana Tauro <riana.tauro@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: riana.tauro@intel.com, anshuman.gupta@intel.com,
rodrigo.vivi@intel.com, aravind.iddamsetty@linux.intel.com,
badal.nilawar@intel.com, raag.jadav@intel.com,
ravi.kishore.koppuravuri@intel.com, mallesh.koujalagi@intel.com,
soham.purkait@intel.com,
Michal Wajdeczko <michal.wajdeczko@intel.com>,
Matthew Brost <matthew.brost@intel.com>,
Matt Roper <matthew.d.roper@intel.com>
Subject: [PATCH v4 02/13] drm/xe/xe_pci_error: Implement PCI error recovery callbacks
Date: Fri, 17 Apr 2026 14:28:14 +0530 [thread overview]
Message-ID: <20260417085812.4013309-17-riana.tauro@intel.com> (raw)
In-Reply-To: <20260417085812.4013309-15-riana.tauro@intel.com>
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>
---
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)
---
drivers/gpu/drm/xe/Makefile | 1 +
drivers/gpu/drm/xe/xe_device.h | 15 ++++
drivers/gpu/drm/xe/xe_device_types.h | 3 +
drivers/gpu/drm/xe/xe_pci.c | 3 +
drivers/gpu/drm/xe/xe_pci_error.c | 107 +++++++++++++++++++++++++++
5 files changed, 129 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 e42e582aca5c..69c233d9a488 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_device.h b/drivers/gpu/drm/xe/xe_device.h
index 555c191f7510..6e18a51e0ade 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -43,6 +43,21 @@ static inline struct xe_device *ttm_to_xe_device(struct ttm_device *ttm)
return container_of(ttm, struct xe_device, ttm);
}
+static inline bool xe_device_is_in_recovery(struct xe_device *xe)
+{
+ return atomic_read(&xe->in_recovery);
+}
+
+static inline void xe_device_set_in_recovery(struct xe_device *xe)
+{
+ atomic_set(&xe->in_recovery, 1);
+}
+
+static inline void xe_device_clear_in_recovery(struct xe_device *xe)
+{
+ atomic_set(&xe->in_recovery, 0);
+}
+
struct xe_device *xe_device_create(struct pci_dev *pdev,
const struct pci_device_id *ent);
int xe_device_probe_early(struct xe_device *xe);
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 150c76b2acaf..c9fe86b670bd 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -494,6 +494,9 @@ struct xe_device {
bool inconsistent_reset;
} wedged;
+ /** @in_recovery: Indicates if device is in recovery */
+ atomic_t in_recovery;
+
/** @bo_device: Struct to control async free of BOs */
struct xe_bo_dev {
/** @bo_device.async_free: Free worker */
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index 6e560ef84a97..7ac433742f82 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -1324,6 +1324,8 @@ 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,
@@ -1331,6 +1333,7 @@ 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..427a8e09408c
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_pci_error.c
@@ -0,0 +1,107 @@
+// 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;
+
+ /* Return if device is wedged or in survivability mode */
+ if (xe_survivability_mode_is_boot_enabled(xe) || xe_device_wedged(xe))
+ return;
+
+ /*
+ * 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;
+
+ xe_device_set_in_recovery(xe);
+
+ 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);
+
+ 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 wipes out all device memory
+ * requiring XE KMD to perform a device removal and reprobe.
+ */
+ pdev->driver->remove(pdev);
+
+ if (!pdev->driver->probe(pdev, ent))
+ return PCI_ERS_RESULT_RECOVERED;
+
+ return PCI_ERS_RESULT_DISCONNECT;
+}
+
+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");
+
+ xe_device_clear_in_recovery(xe);
+}
+
+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,
+};
--
2.47.1
next prev parent reply other threads:[~2026-04-17 8:25 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-17 8:58 [PATCH v4 00/13] Introduce Xe Uncorrectable Error Handling Riana Tauro
2026-04-17 8:58 ` [PATCH v4 01/13] drm/xe/xe_survivability: Decouple survivability info from boot survivability Riana Tauro
2026-04-17 8:58 ` Riana Tauro [this message]
2026-04-27 6:35 ` [PATCH v4 02/13] drm/xe/xe_pci_error: Implement PCI error recovery callbacks Raag Jadav
2026-05-06 13:59 ` Tauro, Riana
2026-04-17 8:58 ` [PATCH v4 03/13] drm/xe/xe_pci_error: Group all devres to release them on PCIe slot reset Riana Tauro
2026-04-17 8:58 ` [PATCH v4 04/13] drm/xe: Skip device access during PCI error recovery Riana Tauro
2026-04-30 12:58 ` Anshuman Gupta
2026-05-06 15:41 ` Tauro, Riana
2026-04-17 8:58 ` [PATCH v4 05/13] drm/xe/xe_ras: Initialize Uncorrectable AER Registers Riana Tauro
2026-04-27 7:56 ` Raag Jadav
2026-05-05 5:22 ` Tauro, Riana
2026-04-17 8:58 ` [PATCH v4 06/13] drm/xe/xe_ras: Add basic structures and commands for uncorrectable errors Riana Tauro
2026-04-17 17:38 ` Matt Roper
2026-04-17 21:25 ` Jadav, Raag
2026-04-17 21:32 ` Matt Roper
2026-04-20 5:34 ` Tauro, Riana
2026-04-20 7:49 ` Raag Jadav
2026-04-17 8:58 ` [PATCH v4 07/13] drm/xe/xe_ras: Add support for uncorrectable core-compute errors Riana Tauro
2026-04-27 8:24 ` Raag Jadav
2026-05-05 5:28 ` Tauro, Riana
2026-04-17 8:58 ` [PATCH v4 08/13] drm/xe/xe_ras: Handle uncorrectable SoC Internal errors Riana Tauro
2026-04-17 8:58 ` [PATCH v4 09/13] drm/xe/xe_ras: Handle uncorrectable device memory errors Riana Tauro
2026-04-21 6:08 ` Upadhyay, Tejas
2026-05-05 5:03 ` Tauro, Riana
2026-04-17 8:58 ` [PATCH v4 10/13] drm/xe/xe_ras: Add support to offline/decline a page Riana Tauro
2026-04-21 6:21 ` Upadhyay, Tejas
2026-05-05 5:16 ` Tauro, Riana
2026-04-17 8:58 ` [PATCH v4 11/13] drm/xe/xe_ras: Add support for page offline list and queue commands Riana Tauro
2026-04-21 6:19 ` Upadhyay, Tejas
2026-05-05 5:08 ` Tauro, Riana
2026-04-21 9:10 ` Upadhyay, Tejas
2026-05-05 5:17 ` Tauro, Riana
2026-04-17 8:58 ` [PATCH v4 12/13] drm/xe/xe_ras: Query errors from system controller on probe Riana Tauro
2026-04-28 11:46 ` Raag Jadav
2026-05-05 13:50 ` Tauro, Riana
2026-04-17 8:58 ` [PATCH v4 13/13] drm/xe/xe_pci_error: Process errors in mmio_enabled Riana Tauro
2026-04-28 11:39 ` Raag Jadav
2026-05-05 5:31 ` Tauro, Riana
2026-04-30 11:15 ` Gupta, Anshuman
2026-05-02 17:55 ` Raag Jadav
2026-04-20 13:33 ` ✗ CI.checkpatch: warning for Introduce Xe Uncorrectable Error Handling (rev4) Patchwork
2026-04-20 13:35 ` ✓ CI.KUnit: success " Patchwork
2026-04-20 14:42 ` ✓ Xe.CI.BAT: " Patchwork
2026-04-20 17:14 ` ✗ Xe.CI.FULL: failure " Patchwork
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260417085812.4013309-17-riana.tauro@intel.com \
--to=riana.tauro@intel.com \
--cc=anshuman.gupta@intel.com \
--cc=aravind.iddamsetty@linux.intel.com \
--cc=badal.nilawar@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=mallesh.koujalagi@intel.com \
--cc=matthew.brost@intel.com \
--cc=matthew.d.roper@intel.com \
--cc=michal.wajdeczko@intel.com \
--cc=raag.jadav@intel.com \
--cc=ravi.kishore.koppuravuri@intel.com \
--cc=rodrigo.vivi@intel.com \
--cc=soham.purkait@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).