x86: calculate maximum host and guest featuresets

All of this information will be used by the toolstack to make informed
levelling decisions for VMs, and by Xen to sanity check toolstack-provided
information.

The split between the shadow and hap HVM masks is necessary due to the lack of
a "get cpuid policy" hypercall.  Multi-host toolstacks (i.e. not libxl)
dealing with hap and non-hap capable hosts need to be able to calculate that
migrating a shadow guest is safe.

Future planned development work will implement proper cpuid policy handing in
Xen, including a "get policy" hypercall, but until then, the difference is
made available for toolstack use via a non-stable interface.

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

xen/arch/x86/cpuid.c

@@ -1,14 +1,176 @@
 #include <xen/init.h>
 #include <xen/lib.h>
 #include <asm/cpuid.h>
+#include <asm/hvm/hvm.h>
+#include <asm/hvm/vmx/vmcs.h>
+#include <asm/processor.h>
 
 const uint32_t known_features[] = INIT_KNOWN_FEATURES;
 const uint32_t special_features[] = INIT_SPECIAL_FEATURES;
 
+static const uint32_t __initconst pv_featuremask[] = INIT_PV_FEATURES;
+static const uint32_t __initconst hvm_shadow_featuremask[] = INIT_HVM_SHADOW_FEATURES;
+static const uint32_t __initconst hvm_hap_featuremask[] = INIT_HVM_HAP_FEATURES;
+
+uint32_t __read_mostly raw_featureset[FSCAPINTS];
+uint32_t __read_mostly pv_featureset[FSCAPINTS];
+uint32_t __read_mostly hvm_featureset[FSCAPINTS];
+
+static void __init sanitise_featureset(uint32_t *fs)
+{
+    unsigned int i;
+
+    for ( i = 0; i < FSCAPINTS; ++i )
+    {
+        /* Clamp to known mask. */
+        fs[i] &= known_features[i];
+    }
+
+    /*
+     * Sort out shared bits.  We are constructing a featureset which needs to
+     * be applicable to a cross-vendor case.  Intel strictly clears the common
+     * bits in e1d, while AMD strictly duplicates them.
+     *
+     * We duplicate them here to be compatible with AMD while on Intel, and
+     * rely on logic closer to the guest to make the featureset stricter if
+     * emulating Intel.
+     */
+    fs[FEATURESET_e1d] = ((fs[FEATURESET_1d]  &  CPUID_COMMON_1D_FEATURES) |
+                          (fs[FEATURESET_e1d] & ~CPUID_COMMON_1D_FEATURES));
+}
+
+static void __init calculate_raw_featureset(void)
+{
+    unsigned int max, tmp;
+
+    max = cpuid_eax(0);
+
+    if ( max >= 1 )
+        cpuid(0x1, &tmp, &tmp,
+              &raw_featureset[FEATURESET_1c],
+              &raw_featureset[FEATURESET_1d]);
+    if ( max >= 7 )
+        cpuid_count(0x7, 0, &tmp,
+                    &raw_featureset[FEATURESET_7b0],
+                    &raw_featureset[FEATURESET_7c0],
+                    &tmp);
+    if ( max >= 0xd )
+        cpuid_count(0xd, 1,
+                    &raw_featureset[FEATURESET_Da1],
+                    &tmp, &tmp, &tmp);
+
+    max = cpuid_eax(0x80000000);
+    if ( (max >> 16) != 0x8000 )
+        return;
+
+    if ( max >= 0x80000001 )
+        cpuid(0x80000001, &tmp, &tmp,
+              &raw_featureset[FEATURESET_e1c],
+              &raw_featureset[FEATURESET_e1d]);
+    if ( max >= 0x80000007 )
+        cpuid(0x80000007, &tmp, &tmp, &tmp,
+              &raw_featureset[FEATURESET_e7d]);
+    if ( max >= 0x80000008 )
+        cpuid(0x80000008, &tmp,
+              &raw_featureset[FEATURESET_e8b],
+              &tmp, &tmp);
+}
+
+static void __init calculate_pv_featureset(void)
+{
+    unsigned int i;
+
+    for ( i = 0; i < FSCAPINTS; ++i )
+        pv_featureset[i] = host_featureset[i] & pv_featuremask[i];
+
+    /* Unconditionally claim to be able to set the hypervisor bit. */
+    __set_bit(X86_FEATURE_HYPERVISOR, pv_featureset);
+
+    /*
+     * Allow the toolstack to set HTT, X2APIC and CMP_LEGACY.  These bits
+     * affect how to interpret topology information in other cpuid leaves.
+     */
+    __set_bit(X86_FEATURE_HTT, pv_featureset);
+    __set_bit(X86_FEATURE_X2APIC, pv_featureset);
+    __set_bit(X86_FEATURE_CMP_LEGACY, pv_featureset);
+
+    sanitise_featureset(pv_featureset);
+}
+
+static void __init calculate_hvm_featureset(void)
+{
+    unsigned int i;
+    const uint32_t *hvm_featuremask;
+
+    if ( !hvm_enabled )
+        return;
+
+    hvm_featuremask = hvm_funcs.hap_supported ?
+        hvm_hap_featuremask : hvm_shadow_featuremask;
+
+    for ( i = 0; i < FSCAPINTS; ++i )
+        hvm_featureset[i] = host_featureset[i] & hvm_featuremask[i];
+
+    /* Unconditionally claim to be able to set the hypervisor bit. */
+    __set_bit(X86_FEATURE_HYPERVISOR, hvm_featureset);
+
+    /*
+     * Allow the toolstack to set HTT, X2APIC and CMP_LEGACY.  These bits
+     * affect how to interpret topology information in other cpuid leaves.
+     */
+    __set_bit(X86_FEATURE_HTT, hvm_featureset);
+    __set_bit(X86_FEATURE_X2APIC, hvm_featureset);
+    __set_bit(X86_FEATURE_CMP_LEGACY, hvm_featureset);
+
+    /*
+     * Xen can provide an APIC emulation to HVM guests even if the host's APIC
+     * isn't enabled.
+     */
+    __set_bit(X86_FEATURE_APIC, hvm_featureset);
+
+    /*
+     * On AMD, PV guests are entirely unable to use SYSENTER as Xen runs in
+     * long mode (and init_amd() has cleared it out of host capabilities), but
+     * HVM guests are able if running in protected mode.
+     */
+    if ( (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) &&
+         test_bit(X86_FEATURE_SEP, raw_featureset) )
+        __set_bit(X86_FEATURE_SEP, hvm_featureset);
+
+    /*
+     * With VT-x, some features are only supported by Xen if dedicated
+     * hardware support is also available.
+     */
+    if ( cpu_has_vmx )
+    {
+        if ( !(vmx_vmexit_control & VM_EXIT_CLEAR_BNDCFGS) ||
+             !(vmx_vmentry_control & VM_ENTRY_LOAD_BNDCFGS) )
+            __clear_bit(X86_FEATURE_MPX, hvm_featureset);
+
+        if ( !cpu_has_vmx_xsaves )
+            __clear_bit(X86_FEATURE_XSAVES, hvm_featureset);
+
+        if ( !cpu_has_vmx_pcommit )
+            __clear_bit(X86_FEATURE_PCOMMIT, hvm_featureset);
+    }
+
+    sanitise_featureset(hvm_featureset);
+}
+
+void __init calculate_featuresets(void)
+{
+    calculate_raw_featureset();
+    calculate_pv_featureset();
+    calculate_hvm_featureset();
+}
+
 static void __init __maybe_unused build_assertions(void)
 {
     BUILD_BUG_ON(ARRAY_SIZE(known_features) != FSCAPINTS);
     BUILD_BUG_ON(ARRAY_SIZE(special_features) != FSCAPINTS);
+    BUILD_BUG_ON(ARRAY_SIZE(pv_featuremask) != FSCAPINTS);
+    BUILD_BUG_ON(ARRAY_SIZE(hvm_shadow_featuremask) != FSCAPINTS);
+    BUILD_BUG_ON(ARRAY_SIZE(hvm_hap_featuremask) != FSCAPINTS);
 }
 
 /*

xen/arch/x86/setup.c

@@ -50,6 +50,7 @@
 #include <asm/nmi.h>
 #include <asm/alternative.h>
 #include <asm/mc146818rtc.h>
+#include <asm/cpuid.h>
 
 /* opt_nosmp: If true, secondary processors are ignored. */
 static bool_t __initdata opt_nosmp;
@@ -1525,6 +1526,8 @@ void __init noreturn __start_xen(unsigned long mbi_p)
                "Multiple initrd candidates, picking module #%u\n",
                initrdidx);
 
+    calculate_featuresets();
+
     /*
      * Temporarily clear SMAP in CR4 to allow user-accesses in construct_dom0().
      * This saves a large number of corner cases interactions with

xen/include/asm-x86/cpuid.h

@@ -6,12 +6,29 @@
 
 #define FSCAPINTS FEATURESET_NR_ENTRIES
 
+#define FEATURESET_1d     0 /* 0x00000001.edx      */
+#define FEATURESET_1c     1 /* 0x00000001.ecx      */
+#define FEATURESET_e1d    2 /* 0x80000001.edx      */
+#define FEATURESET_e1c    3 /* 0x80000001.ecx      */
+#define FEATURESET_Da1    4 /* 0x0000000d:1.eax    */
+#define FEATURESET_7b0    5 /* 0x00000007:0.ebx    */
+#define FEATURESET_7c0    6 /* 0x00000007:0.ecx    */
+#define FEATURESET_e7d    7 /* 0x80000007.edx      */
+#define FEATURESET_e8b    8 /* 0x80000008.ebx      */
+
 #ifndef __ASSEMBLY__
 #include <xen/types.h>
 
 extern const uint32_t known_features[FSCAPINTS];
 extern const uint32_t special_features[FSCAPINTS];
 
+extern uint32_t raw_featureset[FSCAPINTS];
+#define host_featureset boot_cpu_data.x86_capability
+extern uint32_t pv_featureset[FSCAPINTS];
+extern uint32_t hvm_featureset[FSCAPINTS];
+
+void calculate_featuresets(void);
+
 #endif /* __ASSEMBLY__ */
 #endif /* !__X86_CPUID_H__ */