[PATCH v3 1/4] KVM: TDX: Track configurable CPUID bits allowed by KVM

[Binbin Wu]

Add tdx_cpu_cfg_caps[] to track the subset of TDX directly configurable
CPUID feature bits that KVM supports, and build the masks during TDX
hardware setup via tdx_initialize_cpu_cfg_caps().

The TDX module reports the CPUID bits that the VMM can directly configure
for a TD, but KVM cannot blindly expose all reported bits to userspace.
Certain features imply additional architectural state, e.g. one or more
MSRs, that KVM must explicitly manage across host/guest transitions to
prevent host state corruption.

Today KVM relies on a hardcoded denylist, i.e. it clears a few known
problematic bits, e.g. TSX and WAITPKG, and passes everything else through.
A denylist is fundamentally fragile while an allowlist inverts the default,
i.e. unknown configurable bits are hidden and not allowed to be enabled
until KVM explicitly opts in.

Except for a few fixed-1 bits required for basic TDX support, host state
clobbering features are either directly configurable or gated by TD
ATTRIBUTES/XFAM.  Tracking only the directly configurable feature bits is
therefore sufficient to serve the purpose while keeping the code footprint
small.

Organize tdx_cpu_cfg_caps[] following kvm_cpu_caps[] so that the masks can
be built with the similar feature-name based initializers.  CPUID registers
that hold directly configurable non-feature (multi-bit) fields are handled
separately.

The allowlist is consumed by later patches to filter KVM_TDX_CAPABILITIES
and to reject unsupported CPUID input to KVM_TDX_INIT_VM, so that newly
introduced TDX directly configurable CPUID feature bits stay hidden from
userspace until KVM explicitly opts in.

Add comments as placeholders for HLE, RTM and WAITPKG, which KVM doesn't
support for TDX yet.

Signed-off-by: Binbin Wu <binbin.wu@xxxxxxxxxxxxxxx>
---
v3:
- Drop the new data structure in v2 and only track feature bits by
  following the organization of kvm_cpu_caps[], handle non-feature
  bits separately. (Sean)
- Use two versions of macros (TDX_CFG_F() VS. TDX_CFG_EXTRA_F()) to
  distinguish whether a supported TDX configurable CPUID bit should be
  checked against KVM's common cpu capabilities.
- Add AMX_COMPLEX since it has been defined in the CPUID virtualization doc.
---
 arch/x86/kvm/vmx/tdx.c | 145 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 145 insertions(+)

diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index b272c20586a7..d4a3a42cfd9d 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -52,6 +52,149 @@
 	__TDX_BUG_ON(__err, #__fn, __kvm, ", " #a1 " 0x%llx, " #a2 ", 0x%llx, " #a3 " 0x%llx", \
 		     a1, a2, a3)
 
+static u32 tdx_cpu_cfg_caps[NR_KVM_CPU_CAPS] __ro_after_init;
+static_assert(ARRAY_SIZE(tdx_cpu_cfg_caps) == ARRAY_SIZE(kvm_cpu_caps));
+
+#define TDX_VALIDATE_CPU_CAP_USAGE(name)			\
+	BUILD_BUG_ON(__feature_leaf(X86_FEATURE_##name) !=	\
+		     tdx_cpu_cap_init_in_progress)
+
+/* For feature bit that KVM advertised through kvm_cpu_caps[]. */
+#define TDX_CFG_F(name)					\
+({							\
+	TDX_VALIDATE_CPU_CAP_USAGE(name);		\
+	tdx_cfg_caps |= feature_bit(name);		\
+})
+
+/*
+ * For feature bit KVM allows for TDX guests even though it is not advertised
+ * through kvm_cpu_caps[], e.g. MWAIT.
+ */
+#define TDX_CFG_EXTRA_F(name)				\
+({							\
+	TDX_VALIDATE_CPU_CAP_USAGE(name);		\
+	tdx_cfg_extra_caps |= feature_bit(name);	\
+})
+
+#define tdx_cpu_cfg_cap_init(leaf, feature_initializers...)		\
+do {									\
+	const u32 __maybe_unused tdx_cpu_cap_init_in_progress = leaf;	\
+	u32 tdx_cfg_extra_caps = 0;					\
+	u32 tdx_cfg_caps = 0;						\
+									\
+	feature_initializers						\
+	tdx_cpu_cfg_caps[leaf] = (tdx_cfg_caps & kvm_cpu_caps[leaf]) |	\
+				 tdx_cfg_extra_caps;			\
+} while (0)
+
+/*
+ * Track only CPUID feature bits that are directly configurable by userspace.
+ * Features controlled by XFAM or ATTRIBUTES are excluded; userspace cannot
+ * enable them until KVM adds support for the corresponding control.
+ */
+static void __init tdx_initialize_cpu_cfg_caps(void)
+{
+	tdx_cpu_cfg_cap_init(CPUID_1_ECX,
+		TDX_CFG_EXTRA_F(MWAIT),
+		TDX_CFG_F(TSC_DEADLINE_TIMER),
+		TDX_CFG_F(AVX),
+		TDX_CFG_F(F16C),
+	);
+
+	tdx_cpu_cfg_cap_init(CPUID_1_EDX,
+		TDX_CFG_F(MCE),
+		TDX_CFG_F(MTRR),
+		TDX_CFG_F(MCA),
+		TDX_CFG_F(SELFSNOOP),
+	);
+
+	tdx_cpu_cfg_cap_init(CPUID_7_0_EBX,
+		TDX_CFG_F(BMI1),
+		/* HLE */
+		TDX_CFG_F(BMI2),
+		TDX_CFG_F(ERMS),
+		/* RTM */
+		TDX_CFG_F(AVX512F),
+		TDX_CFG_F(AVX512DQ),
+		TDX_CFG_F(ADX),
+		TDX_CFG_F(AVX512IFMA),
+		TDX_CFG_F(AVX512PF),
+		TDX_CFG_F(AVX512ER),
+		TDX_CFG_F(AVX512CD),
+		TDX_CFG_F(AVX512BW),
+		TDX_CFG_F(AVX512VL),
+	);
+
+	tdx_cpu_cfg_cap_init(CPUID_7_ECX,
+		TDX_CFG_F(UMIP),
+		/* WAITPKG */
+		TDX_CFG_F(AVX512_VBMI2),
+		TDX_CFG_F(GFNI),
+		TDX_CFG_F(VAES),
+		TDX_CFG_F(VPCLMULQDQ),
+		TDX_CFG_F(AVX512_VNNI),
+		TDX_CFG_F(AVX512_BITALG),
+		TDX_CFG_F(AVX512_VPOPCNTDQ),
+		TDX_CFG_F(LA57),
+		TDX_CFG_F(RDPID),
+		TDX_CFG_F(CLDEMOTE),
+	);
+
+	tdx_cpu_cfg_cap_init(CPUID_7_EDX,
+		TDX_CFG_F(AVX512_4VNNIW),
+		TDX_CFG_F(AVX512_4FMAPS),
+		TDX_CFG_F(FSRM),
+		TDX_CFG_F(AVX512_VP2INTERSECT),
+		TDX_CFG_F(SERIALIZE),
+		TDX_CFG_F(TSXLDTRK),
+	);
+
+	tdx_cpu_cfg_cap_init(CPUID_7_1_EAX,
+		TDX_CFG_F(SHA512),
+		TDX_CFG_F(SM3),
+		TDX_CFG_F(SM4),
+		TDX_CFG_F(AVX_VNNI),
+		TDX_CFG_F(AVX512_BF16),
+		TDX_CFG_F(CMPCCXADD),
+		TDX_CFG_F(FZRM),
+		TDX_CFG_F(FSRS),
+		TDX_CFG_F(FSRC),
+		TDX_CFG_F(LKGS),
+		TDX_CFG_F(WRMSRNS),
+		TDX_CFG_F(AMX_FP16),
+		TDX_CFG_F(AVX_IFMA),
+		TDX_CFG_F(LAM),
+		TDX_CFG_F(MOVRS),
+	);
+
+	tdx_cpu_cfg_cap_init(CPUID_7_1_EDX,
+		TDX_CFG_F(AVX_VNNI_INT8),
+		TDX_CFG_F(AVX_NE_CONVERT),
+		TDX_CFG_F(AMX_COMPLEX),
+		TDX_CFG_F(AVX_VNNI_INT16),
+		TDX_CFG_F(PREFETCHITI),
+		TDX_CFG_F(AVX10),
+	);
+
+	tdx_cpu_cfg_cap_init(CPUID_7_2_EDX,
+		TDX_CFG_F(DDPD_U),
+		TDX_CFG_F(MCDT_NO),
+	);
+
+	tdx_cpu_cfg_cap_init(CPUID_1E_1_EAX,
+		TDX_CFG_F(AMX_FP8),
+		TDX_CFG_F(AMX_TF32),
+		TDX_CFG_F(AMX_AVX512),
+		TDX_CFG_F(AMX_MOVRS),
+	);
+
+	tdx_cpu_cfg_cap_init(CPUID_8000_0008_EBX,
+		TDX_CFG_F(WBNOINVD),
+	);
+}
+
+#undef TDX_CFG_F
+#undef TDX_CFG_EXTRA_F
 
 bool enable_tdx __ro_after_init;
 module_param_named(tdx, enable_tdx, bool, 0444);
@@ -3481,6 +3624,8 @@ int __init tdx_hardware_setup(void)
 		return r;
 	}
 
+	tdx_initialize_cpu_cfg_caps();
+
 	KVM_SANITY_CHECK_VM_STRUCT_SIZE(kvm_tdx);
 
 	vt_x86_ops.vm_size = max_t(unsigned int, vt_x86_ops.vm_size, sizeof(struct kvm_tdx));
-- 
2.46.0