The system PM notifier runs before the PCI suspend callback and may evict BOs or submit migration work. This work must not start after the device has been declared wedged.
Skip PM preparation for a wedged device. Track whether preparation ran so the post callback only performs matching cleanup and releases the runtime PM reference when needed. Cc: Matthew Brost <[email protected]> Cc: Thomas Hellström <[email protected]> Cc: Himal Prasad Ghimiray <[email protected]> Cc: Rodrigo Vivi <[email protected]> Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Arvind Yadav <[email protected]> --- drivers/gpu/drm/xe/xe_device_types.h | 2 ++ drivers/gpu/drm/xe/xe_pm.c | 10 ++++++++++ 2 files changed, 12 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 508ba3872e72..c9dc417878e7 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -471,6 +471,8 @@ struct xe_device { /** @pm_notifier: Our PM notifier to perform actions in response to various PM events. */ struct notifier_block pm_notifier; + /** @pm_notifier_active: PM notifier prepare work was performed */ + bool pm_notifier_active; /** @pm_block: Completion to block validating tasks on suspend / hibernate prepare */ struct completion pm_block; /** @rebind_resume_list: List of wq items to kick on resume. */ diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index 720e083cd279..dd7fd170bc94 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -457,9 +457,14 @@ static int xe_pm_notifier_callback(struct notifier_block *nb, { struct xe_validation_ctx ctx; + /* Do not start PM preparation after a wedge is declared. */ + if (xe_device_wedged(xe)) + break; + reinit_completion(&xe->pm_block); xe_pm_block_begin_signalling(); xe_pm_runtime_get(xe); + xe->pm_notifier_active = true; (void)xe_validation_ctx_init(&ctx, &xe->val, NULL, (struct xe_val_flags) {.exclusive = true}); err = xe_bo_evict_all_user(xe); @@ -480,6 +485,11 @@ static int xe_pm_notifier_callback(struct notifier_block *nb, } case PM_POST_HIBERNATION: case PM_POST_SUSPEND: + if (!xe->pm_notifier_active) + break; + + xe->pm_notifier_active = false; + complete_all(&xe->pm_block); xe_pm_wake_rebind_workers(xe); xe_bo_notifier_unprepare_all_pinned(xe); -- 2.43.0
