svn commit: r198341 - in head/sys: amd64/amd64 arm/arm arm/mv i386/i386 i386/xen ia64/ia64 kern mips/mips powerpc/aim powerpc/booke powerpc/include powerpc/powerpc sparc64/sparc64 sun4v/sun4v vm

Marcel Moolenaar xcllnt at mac.com
Mon Oct 26 20:53:50 UTC 2009


On Oct 26, 2009, at 1:11 PM, Marius Strobl wrote:

> The cheetah-class CPUs, i.e. USIII and later, take care of
> I$ coherency themselves, unlike the spitfire ones (see also
> cheetah_icache_page_inval() vs. spitfire_icache_page_inval()).

This explains why I didn't see any I-cache coherency issues :-)

> I currently can't think of any existing code which would
> ensure I$ consistency after the writes have been performed,
> not even as a side-effect. The proper solution probalby is to
> make pmap_sync_icache() a wrapper around icache_page_inval().

I concur. Do we have any spitfire-based sparc64 boxes in the
cluster or do you have one?

-- 
Marcel Moolenaar
xcllnt at mac.com





More information about the svn-src-head mailing list