On Mon, 2010-10-18 at 16:57 -0500, Dave Kleikamp wrote:
>
> I didn't like the implementation of a per-core stale map. The existing
> implementation flushes the core's tlb, but only clears a specific entry
> from the stale map. It's dealing with the stale contexts one at a time,
> where the new f
On Thu, 2010-10-14 at 11:52 +1100, Benjamin Herrenschmidt wrote:
> On Fri, 2010-09-24 at 13:01 -0500, Dave Kleikamp wrote:
> > On PPC_MMU_NOHASH processors that support a large number of contexts,
> > implement a lazy flush_tlb_mm() that switches to a free context, marking
> > the old one stale. T
On Fri, 2010-09-24 at 13:01 -0500, Dave Kleikamp wrote:
> On PPC_MMU_NOHASH processors that support a large number of contexts,
> implement a lazy flush_tlb_mm() that switches to a free context, marking
> the old one stale. The tlb is only flushed when no free contexts are
> available.
>
> The la
On PPC_MMU_NOHASH processors that support a large number of contexts,
implement a lazy flush_tlb_mm() that switches to a free context, marking
the old one stale. The tlb is only flushed when no free contexts are
available.
The lazy tlb flushing is controlled by the global variable tlb_lazy_flush
