preempt bug in set_pmd_pfn?

[Jeremy Fitzhardinge <jeremy@goop.org>]

I think set_pmd_pfn, which is only called by __set_fixmap, might have a 
preempt bug in it.

It can be executed with preemption enabled, but what if it gets preempted

	set_pmd(pmd, pfn_pmd(pfn, flags));
	/*
	 * It's enough to flush this one mapping.
	 * (PGE mappings get flushed as well)
	 */
>here<
	__flush_tlb_one(vaddr);
}

?


Won't this leave a stale tlb on the old processor?

I noticed this because the Xen tlb flushing code effectively has a 
smp_processor_id(), which provokes a warning when preemption is 
enabled.  It seems to me that it never makes sense to be doing a tlb 
flush unless you know which processor you're actually running on...

    J