On Fri, Aug 24, 2012 at 2:33 PM, H. Peter Anvin <h...@zytor.com> wrote: > I have applied this to tip:x86/fpu, but I have also asked Suresh to > prepare a followon patch to decouple eager save from the existence of > the XSAVE instruction. It seems pretty clear that eager save is a net > benefit in the presence of the XSAVEOPT, but it isn't as clear for only > having XSAVE, as far as I can tell. Either way it would seem to be a > policy decision that is somewhat separate from the exact instruction.
Agreed. It would also be good for testing bugs and/or performance for both xsave and non-xsave cases. Linus -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/