drm/xe: Do not wake device during a GT reset

Waking the device during a GT reset can lead to unintended memory
allocation, which is not allowed since GT resets occur in the reclaim
path. Prevent this by holding a PM reference while a reset is in flight.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: stable@vger.kernel.org
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20251022005538.828980-3-matthew.brost@intel.com
(cherry picked from commit 480b358e7d8ef69fd8f1b0cad6e07c7d70a36ee4)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 3e0ad7e5b5dfbae711ad153a7b588d155b52abf7..6d3db5e55d98ae3dcf9fb4a3a766edd34ab2302e 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -813,12 +813,16 @@ static int gt_reset(struct xe_gt *gt)
        unsigned int fw_ref;
        int err;
 
-       if (xe_device_wedged(gt_to_xe(gt)))
-               return -ECANCELED;
+       if (xe_device_wedged(gt_to_xe(gt))) {
+               err = -ECANCELED;
+               goto err_pm_put;
+       }
 
        /* We only support GT resets with GuC submission */
-       if (!xe_device_uc_enabled(gt_to_xe(gt)))
-               return -ENODEV;
+       if (!xe_device_uc_enabled(gt_to_xe(gt))) {
+               err = -ENODEV;
+               goto err_pm_put;
+       }
 
        xe_gt_info(gt, "reset started\n");
 
@@ -826,8 +830,6 @@ static int gt_reset(struct xe_gt *gt)
        if (!err)
                xe_gt_warn(gt, "reset block failed to get lifted");
 
-       xe_pm_runtime_get(gt_to_xe(gt));
-
        if (xe_fault_inject_gt_reset()) {
                err = -ECANCELED;
                goto err_fail;
@@ -874,6 +876,7 @@ err_fail:
        xe_gt_err(gt, "reset failed (%pe)\n", ERR_PTR(err));
 
        xe_device_declare_wedged(gt_to_xe(gt));
+err_pm_put:
        xe_pm_runtime_put(gt_to_xe(gt));
 
        return err;
@@ -895,7 +898,9 @@ void xe_gt_reset_async(struct xe_gt *gt)
                return;
 
        xe_gt_info(gt, "reset queued\n");
-       queue_work(gt->ordered_wq, &gt->reset.worker);
+       xe_pm_runtime_get_noresume(gt_to_xe(gt));
+       if (!queue_work(gt->ordered_wq, &gt->reset.worker))
+               xe_pm_runtime_put(gt_to_xe(gt));
 }
 
 void xe_gt_suspend_prepare(struct xe_gt *gt)