KVM: x86: Add support for reverse CPUID lookup of scattered features

Introduce a scheme that allows KVM's CPUID magic to support features
that are scattered in the kernel's feature words.  To advertise and/or
query guest support for CPUID-based features, KVM requires the bit
number of an X86_FEATURE_* to match the bit number in its associated
CPUID entry.  For scattered features, this does not hold true.

Add a framework to allow defining KVM-only words, stored in
kvm_cpu_caps after the shared kernel caps, that can be used to gather
the scattered feature bits by translating X86_FEATURE_* flags into their
KVM-defined feature.

Note, because reverse_cpuid_check() effectively forces kvm_cpu_caps
lookups to be resolved at compile time, there is no runtime cost for
translating from kernel-defined to kvm-defined features.

More details here:  https://lkml.kernel.org/r/X/jxCOLG+HUO4QlZ@google.com

Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Message-Id: <16cad8d00475f67867fb36701fc7fb7c1ec86ce1.1618196135.git.kai.huang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 27 insertions, 5 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 6bd2f8b830e4..1544c35b8e2b 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -28,7 +28,7 @@
  * Unlike "struct cpuinfo_x86.x86_capability", kvm_cpu_caps doesn't need to be
  * aligned to sizeof(unsigned long) because it's not accessed via bitops.
  */
-u32 kvm_cpu_caps[NCAPINTS] __read_mostly;
+u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly;
 EXPORT_SYMBOL_GPL(kvm_cpu_caps);
 
 static u32 xstate_required_size(u64 xstate_bv, bool compacted)
@@ -53,6 +53,7 @@ static u32 xstate_required_size(u64 xstate_bv, bool compacted)
 }
 
 #define F feature_bit
+#define SF(name) (boot_cpu_has(X86_FEATURE_##name) ? F(name) : 0)
 
 static inline struct kvm_cpuid_entry2 *cpuid_entry2_find(
 	struct kvm_cpuid_entry2 *entries, int nent, u32 function, u32 index)
@@ -347,13 +348,13 @@ out:
 	return r;
 }
 
-static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask)
+/* Mask kvm_cpu_caps for @leaf with the raw CPUID capabilities of this CPU. */
+static __always_inline void __kvm_cpu_cap_mask(enum cpuid_leafs leaf)
 {
 	const struct cpuid_reg cpuid = x86_feature_cpuid(leaf * 32);
 	struct kvm_cpuid_entry2 entry;
 
 	reverse_cpuid_check(leaf);
-	kvm_cpu_caps[leaf] &= mask;
 
 	cpuid_count(cpuid.function, cpuid.index,
 		    &entry.eax, &entry.ebx, &entry.ecx, &entry.edx);
@@ -361,6 +362,26 @@ static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask)
 	kvm_cpu_caps[leaf] &= *__cpuid_entry_get_reg(&entry, cpuid.reg);
 }
 
+static __always_inline void kvm_cpu_cap_init_scattered(enum cpuid_leafs leaf, u32 mask)
+{
+	/* Use kvm_cpu_cap_mask for non-scattered leafs. */
+	BUILD_BUG_ON(leaf < NCAPINTS);
+
+	kvm_cpu_caps[leaf] = mask;
+
+	__kvm_cpu_cap_mask(leaf);
+}
+
+static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask)
+{
+	/* Use kvm_cpu_cap_init_scattered for scattered leafs. */
+	BUILD_BUG_ON(leaf >= NCAPINTS);
+
+	kvm_cpu_caps[leaf] &= mask;
+
+	__kvm_cpu_cap_mask(leaf);
+}
+
 void kvm_set_cpu_caps(void)
 {
 	unsigned int f_nx = is_efer_nx() ? F(NX) : 0;
@@ -371,12 +392,13 @@ void kvm_set_cpu_caps(void)
 	unsigned int f_gbpages = 0;
 	unsigned int f_lm = 0;
 #endif
+	memset(kvm_cpu_caps, 0, sizeof(kvm_cpu_caps));
 
-	BUILD_BUG_ON(sizeof(kvm_cpu_caps) >
+	BUILD_BUG_ON(sizeof(kvm_cpu_caps) - (NKVMCAPINTS * sizeof(*kvm_cpu_caps)) >
 		     sizeof(boot_cpu_data.x86_capability));
 
 	memcpy(&kvm_cpu_caps, &boot_cpu_data.x86_capability,
-	       sizeof(kvm_cpu_caps));
+	       sizeof(kvm_cpu_caps) - (NKVMCAPINTS * sizeof(*kvm_cpu_caps)));
 
 	kvm_cpu_cap_mask(CPUID_1_ECX,
 		/*