drm/i915/guc: Handle race condition where wakeref count drops below 0

From Jesus Narvaez
798fd944fbcffdfffeef0b7a5cfdfab1c9dbc56b in linux-6.12.y/6.12.34
0323a5127e7c534cfc88efe0f850a0cb777e938b in mainline linux

Author: jonathangray

sys/dev/pci/drm/i915/gt/uc/intel_guc_submission.c

@@ -3422,18 +3422,29 @@ static inline int guc_lrc_desc_unpin(struct intel_context *ce)
 	 * GuC is active, lets destroy this context, but at this point we can still be racing
 	 * with suspend, so we undo everything if the H2G fails in deregister_context so
 	 * that GuC reset will find this context during clean up.
+	 *
+	 * There is a race condition where the reset code could have altered
+	 * this context's state and done a wakeref put before we try to
+	 * deregister it here. So check if the context is still set to be
+	 * destroyed before undoing earlier changes, to avoid two wakeref puts
+	 * on the same context.
 	 */
 	ret = deregister_context(ce, ce->guc_id.id);
 	if (ret) {
+		bool pending_destroyed;
 		spin_lock_irqsave(&ce->guc_state.lock, flags);
-		set_context_registered(ce);
-		clr_context_destroyed(ce);
+		pending_destroyed = context_destroyed(ce);
+		if (pending_destroyed) {
+			set_context_registered(ce);
+			clr_context_destroyed(ce);
+		}
 		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 		/*
 		 * As gt-pm is awake at function entry, intel_wakeref_put_async merely decrements
 		 * the wakeref immediately but per function spec usage call this after unlock.
 		 */
-		intel_wakeref_put_async(&gt->wakeref);
+		if (pending_destroyed)
+			intel_wakeref_put_async(&gt->wakeref);
 	}
 
 	return ret;