that's just the profiling interrupt hitting them. You should not analyze irq-safe code with a non-NMI profiling interrupt.Hm... I rather thought that the cli would cause a rather large hit on the pipeline and certainly on OOE. Is your observation based on any particular instruction stream? Sti, on the otherhand should be fast...
CLI/STI is extremely fast. (In fact in the -rt tree i'm using them within mutexes instead of preempt_enable()/preempt_disable(), because they are faster and generate less register side-effect.)