| Message ID | 20210708170641.49410-1-michael.roth@amd.com |
|---|---|
| State | New |
| Headers | show |
| Series | target/i386: Fix cpuid level for AMD | expand |
On Thu, Jul 08, 2021 at 12:06:41PM -0500, Michael Roth wrote: > From: zhenwei pi <pizhenwei@bytedance.com> > > A AMD server typically has cpuid level 0x10(test on Rome/Milan), it > should not be changed to 0x1f in multi-dies case. > > Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> > Cc: Eduardo Habkost <ehabkost@redhat.com> > Cc: Richard Henderson <richard.henderson@linaro.org> > Cc: Igor Mammedov <imammedo@redhat.com> > Cc: zhenwei pi <pizhenwei@bytedance.com> > Fixes: a94e1428991 (target/i386: Add CPUID.1F generation support for multi-dies PCMachine) > Signed-off-by: zhenwei pi <pizhenwei@bytedance.com> > * to maintain compatibility with older machine types, only implement > this change when the CPU's "x-vendor-cpuid-only" property is false > Signed-off-by: Michael Roth <michael.roth@amd.com> Queued, thanks!
diff --git a/target/i386/cpu.c b/target/i386/cpu.c index 0b6c921e5a..289dd2b1d8 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -5950,8 +5950,15 @@ void x86_cpu_expand_features(X86CPU *cpu, Error **errp) } } - /* CPU topology with multi-dies support requires CPUID[0x1F] */ - if (env->nr_dies > 1) { + /* + * Intel CPU topology with multi-dies support requires CPUID[0x1F]. + * For AMD Rome/Milan, cpuid level is 0x10, and guest OS should detect + * extended toplogy by leaf 0xB. Only adjust it for Intel CPU, unless + * cpu->vendor_cpuid_only has been unset for compatibility with older + * machine types. + */ + if ((env->nr_dies > 1) && + (IS_INTEL_CPU(env) || !cpu->vendor_cpuid_only)) { x86_cpu_adjust_level(cpu, &env->cpuid_min_level, 0x1F); }