I'm toying an idea to just bump ASID of target process in that
R4000 cache case.  Does it work?  Comments, please.

>> I failed to consider of modifying instructions in text segment.
>>   ...
>> pmap_procwr() is also called mips/mips/procfs_mem.c and I see software
>> breakpointing is a trouble source.  I suspect the issue can be solved
>> in other ways.
>
> I think the I$-barrier operation has to be done in the target process
> context when it resumes excution after the text space was changed by
> others (it would imply full scale I$ invalidation).

Tohru Nishimura