drm/xe: Avoid memory allocations in xe_device_declare_wedged()

xe_device_declare_wedged() runs in the DMA-fence signaling path, where
GFP_KERNEL memory allocations are not allowed. However, registering
xe_device_wedged_fini via drmm_add_action_or_reset() triggers a
GFP_KERNEL allocation.

Fix this by deferring the registration of xe_device_wedged_fini until
late in the driver load sequence. Additionally, drop the wedged PM
reference only if the device is actually wedged in
xe_device_wedged_fini.

Fixes: 452bca0edbd0 ("drm/xe: Don't suspend device upon wedge")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patch.msgid.link/20260326210116.202585-2-matthew.brost@intel.com
(cherry picked from commit b08ceb443866808b881b12d4183008d214d816c1)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 52ee24e9cd3af28381588e10c3897c1a6100a1ed..3eb06b27db7eee0ab9582dbc176ef6c44f4aaa18 100644 (file)
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -837,6 +837,14 @@ static void detect_preproduction_hw(struct xe_device *xe)
        }
 }
 
+static void xe_device_wedged_fini(struct drm_device *drm, void *arg)
+{
+       struct xe_device *xe = arg;
+
+       if (atomic_read(&xe->wedged.flag))
+               xe_pm_runtime_put(xe);
+}
+
 int xe_device_probe(struct xe_device *xe)
 {
        struct xe_tile *tile;
@@ -1013,6 +1021,10 @@ int xe_device_probe(struct xe_device *xe)
 
        detect_preproduction_hw(xe);
 
+       err = drmm_add_action_or_reset(&xe->drm, xe_device_wedged_fini, xe);
+       if (err)
+               goto err_unregister_display;
+
        return devm_add_action_or_reset(xe->drm.dev, xe_device_sanitize, xe);
 
 err_unregister_display:
@@ -1216,13 +1228,6 @@ u64 xe_device_uncanonicalize_addr(struct xe_device *xe, u64 address)
        return address & GENMASK_ULL(xe->info.va_bits - 1, 0);
 }
 
-static void xe_device_wedged_fini(struct drm_device *drm, void *arg)
-{
-       struct xe_device *xe = arg;
-
-       xe_pm_runtime_put(xe);
-}
-
 /**
  * DOC: Xe Device Wedging
  *
@@ -1300,15 +1305,9 @@ void xe_device_declare_wedged(struct xe_device *xe)
                return;
        }
 
-       xe_pm_runtime_get_noresume(xe);
-
-       if (drmm_add_action_or_reset(&xe->drm, xe_device_wedged_fini, xe)) {
-               drm_err(&xe->drm, "Failed to register xe_device_wedged_fini clean-up. Although device is wedged.\n");
-               return;
-       }
-
        if (!atomic_xchg(&xe->wedged.flag, 1)) {
                xe->needs_flr_on_fini = true;
+               xe_pm_runtime_get_noresume(xe);
                drm_err(&xe->drm,
                        "CRITICAL: Xe has declared device %s as wedged.\n"
                        "IOCTLs and executions are blocked. Only a rebind may clear the failure\n"