Re: please revert bogus patch to vmscan.c

[Giuliano Pochini]

>> But of course going from page flush to the mm flush is fine from my part
>> too. As Linus noted a few days ago during swapout we're going to block
>> and reschedule all the time, so the range flush is going to be a noop in
> 
> Only on architectures where the TLB (or equivalent) is
> small and only capable of holding entries for one address
> space at a time.
> 
> It's simply not true on eg PPC.

#ifdef ?

Bye.