On Fri, Oct 19, 2012 at 01:34:19AM +0200, Andre Przywara wrote: > On 10/18/12 18:33, Eduardo Habkost wrote: > >On Wed, Oct 17, 2012 at 11:17:26PM +0200, Andre Przywara wrote: > >>Update QEMU's knowledge of CPUID bit names. This allows to > >>enable/disable those new features on QEMU's command line when > >>using KVM and prepares future feature enablement in QEMU. > ... > >>@@ -79,10 +79,10 @@ static const char *ext3_feature_name[] = { > >> "lahf_lm" /* AMD LahfSahf */, "cmp_legacy", "svm", "extapic" /* AMD > >> ExtApicSpace */, > >> "cr8legacy" /* AMD AltMovCr8 */, "abm", "sse4a", "misalignsse", > >> "3dnowprefetch", "osvw", "ibs", "xop", > >>- "skinit", "wdt", NULL, NULL, > >>- "fma4", NULL, "cvt16", "nodeid_msr", > >>- NULL, NULL, NULL, NULL, > >>- NULL, NULL, NULL, NULL, > >>+ "skinit", "wdt", NULL, "lwp", > >>+ "fma4", "tce", NULL, "nodeid_msr", > > > >You removed cvt16, here. > > On purpose, cvt16 is dead. It seems to have been advertised in the > documentation for some time, but later disappeared. The respective > instructions are now reported via the F16C flag in the Intel leaf. > > If you want to know more, I can dig deeper and ask some people. But > the bit is now "reserved" and was never '1' in any silicon. (And was > introduced by me into QEMU :-(
KVM doesn't report it on GET_SUPPORTED_CPUID, either, so it's impossible to have any VM running with that bit set, even if was set on some silicon. It would be interesting to document that on the commit message, though. > > > > >All the rest of the flags look OK to me. > > Thanks. > > Regards, > Andre. > > -- Eduardo