x86/intel: Expose MSR_ARCH_CAPS to dom0

The overhead of (the lack of) MDS_NO alone has been measured at 30% on some
workloads.  While we're not in a position yet to offer MSR_ARCH_CAPS generally
to guests, dom0 doesn't migrate, so we can pass a subset of hardware values
straight through.

This will cause PVH dom0's not to use KPTI by default, and all dom0's not to
use VERW flushing by default, and to use eIBRS in preference to retpoline on
recent Intel CPUs.

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

xen/arch/x86/cpuid.c

@@ -719,6 +719,14 @@ int init_domain_cpuid_policy(struct domain *d)
     if ( d->disable_migrate )
         p->extd.itsc = cpu_has_itsc;
 
+    /*
+     * Expose the "hardware speculation behaviour" bits of ARCH_CAPS to dom0,
+     * so dom0 can turn off workarounds as appropriate.  Temporary, until the
+     * domain policy logic gains a better understanding of MSRs.
+     */
+    if ( is_hardware_domain(d) && boot_cpu_has(X86_FEATURE_ARCH_CAPS) )
+        p->feat.arch_caps = true;
+
     d->arch.cpuid = p;
 
     recalculate_cpuid_policy(d);

xen/arch/x86/msr.c

@@ -130,6 +130,22 @@ int init_domain_msr_policy(struct domain *d)
     if ( !opt_dom0_cpuid_faulting && is_control_domain(d) && is_pv_domain(d) )
         mp->platform_info.cpuid_faulting = false;
 
+    /*
+     * Expose the "hardware speculation behaviour" bits of ARCH_CAPS to dom0,
+     * so dom0 can turn off workarounds as appropriate.  Temporary, until the
+     * domain policy logic gains a better understanding of MSRs.
+     */
+    if ( is_hardware_domain(d) && boot_cpu_has(X86_FEATURE_ARCH_CAPS) )
+    {
+        uint64_t val;
+
+        rdmsrl(MSR_ARCH_CAPABILITIES, val);
+
+        mp->arch_caps.raw = val &
+            (ARCH_CAPS_RDCL_NO | ARCH_CAPS_IBRS_ALL | ARCH_CAPS_RSBA |
+             ARCH_CAPS_SSB_NO | ARCH_CAPS_MDS_NO | ARCH_CAPS_TAA_NO);
+    }
+
     d->arch.msr = mp;
 
     return 0;