Quoting Mika Kuoppala (2018-05-07 13:09:20) > Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> writes: > > > Around request submission, we protect the call to schedule with a > > premption disable loop to prevent set-wedge chaning function pointers > > s/premption/preemption > s/chaning/changing > > Also RCU read critical sections can be preempted if CONFIG_PREEMPT_RCU > so it looks like we should have had explicit preempt_disable() > before the rcu_read_lock(), if it is the preempt disable we rely on? No, my mistake in not knowing about PREEMPT_RCU. So we need both. Sigh. -Chris _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
