On Tue, 2007-11-20 at 07:26 +0100, Nick Piggin wrote:
>
> BTW, here is another thing which you might want to think about. Again
> untested for temporary lack of hardware.
>
> --
>
> The radix-tree is now RCU safe, so powerpc can avoid the games it was playing
> in order to have a lockless reads
On Tue, Nov 20, 2007 at 05:08:24PM +1100, Benjamin Herrenschmidt wrote:
>
> On Tue, 2007-11-20 at 06:09 +0100, Nick Piggin wrote:
> > This isn't a bugfix, but may help performance slightly...
> >
> > --
> > powerpc 64-bit hash pte lock bit is an actual lock, so it can take advantage
> > of lock b
On Tue, 2007-11-20 at 06:09 +0100, Nick Piggin wrote:
> This isn't a bugfix, but may help performance slightly...
>
> --
> powerpc 64-bit hash pte lock bit is an actual lock, so it can take advantage
> of lock bitops for slightly more optimal memory barriers (can avoid an lwsync
> in the trylock)
This isn't a bugfix, but may help performance slightly...
--
powerpc 64-bit hash pte lock bit is an actual lock, so it can take advantage
of lock bitops for slightly more optimal memory barriers (can avoid an lwsync
in the trylock).
Signed-off-by: Nick Piggin <[EMAIL PROTECTED]>
Acked-by: Benjami
