KVM: x86: Advertise AVX10.1 CPUID to userspace

Advertise AVX10.1 related CPUIDs, i.e. report AVX10 support bit via
CPUID.(EAX=07H, ECX=01H):EDX[bit 19] and new CPUID leaf 0x24H so that
guest OS and applications can query the AVX10.1 CPUIDs directly. Intel
AVX10 represents the first major new vector ISA since the introduction of
Intel AVX512, which will establish a common, converged vector instruction
set across all Intel architectures[1].

AVX10.1 is an early version of AVX10, that enumerates the Intel AVX512
instruction set at 128, 256, and 512 bits which is enabled on
Granite Rapids. I.e., AVX10.1 is only a new CPUID enumeration with no
new functionality.   New features, e.g. Embedded Rounding and Suppress
All Exceptions (SAE) will be introduced in AVX10.2.

Advertising AVX10.1 is safe because there is nothing to enable for AVX10.1,
i.e. it's purely a new way to enumerate support, thus there will never be
anything for the kernel to enable. Note just the CPUID checking is changed
when using AVX512 related instructions, e.g. if using one AVX512
instruction needs to check (AVX512 AND AVX512DQ), it can check
((AVX512 AND AVX512DQ) OR AVX10.1) after checking XCR0[7:5].

The versions of AVX10 are expected to be inclusive, e.g. version N+1 is
a superset of version N. Per the spec, the version can never be 0, just
advertise AVX10.1 if it's supported in hardware. Moreover, advertising
AVX10_{128,256,512} needs to land in the same commit as advertising basic
AVX10.1 support, otherwise KVM would advertise an impossible CPU model.
E.g. a CPU with AVX512 but not AVX10.1/512 is impossible per the SDM.

As more and more AVX related CPUIDs are added (it would have resulted in
around 40-50 CPUID flags when developing AVX10), the versioning approach
is introduced. But incrementing version numbers are bad for virtualization.
E.g. if AVX10.2 has a feature that shouldn't be enumerated to guests for
whatever reason, then KVM can't enumerate any "later" features either,
because the only way to hide the problematic AVX10.2 feature is to set the
version to AVX10.1 or lower[2]. But most AVX features are just passed
through and don't have virtualization controls, so AVX10 should not be
problematic in practice, so long as Intel honors their promise that future
versions will be supersets of past versions.

[1] https://cdrdv2.intel.com/v1/dl/getContent/784267
[2] https://lore.kernel.org/all/Zkz5Ak0PQlAN8DxK@google.com/Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Tao Su <tao1.su@linux.intel.com>
Link: https://lore.kernel.org/r/20240819062327.3269720-1-tao1.su@linux.intel.com
[sean: minor changelog tweaks]
Signed-off-by: Sean Christopherson <seanjc@google.com>

arch/x86/include/asm/cpuid.h

@@ -179,6 +179,7 @@ static __always_inline bool cpuid_function_is_indexed(u32 function)
 	case 0x1d:
 	case 0x1e:
 	case 0x1f:
+	case 0x24:
 	case 0x8000001d:
 		return true;
 	}

arch/x86/kvm/cpuid.c

@@ -705,7 +705,7 @@ void kvm_set_cpu_caps(void)
 
 	kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX,
 		F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(PREFETCHITI) |
-		F(AMX_COMPLEX)
+		F(AMX_COMPLEX) | F(AVX10)
 	);
 
 	kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX,
@@ -721,6 +721,10 @@ void kvm_set_cpu_caps(void)
 		SF(SGX1) | SF(SGX2) | SF(SGX_EDECCSSA)
 	);
 
+	kvm_cpu_cap_init_kvm_defined(CPUID_24_0_EBX,
+		F(AVX10_128) | F(AVX10_256) | F(AVX10_512)
+	);
+
 	kvm_cpu_cap_mask(CPUID_8000_0001_ECX,
 		F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ |
 		F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
@@ -949,7 +953,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 	switch (function) {
 	case 0:
 		/* Limited to the highest leaf implemented in KVM. */
-		entry->eax = min(entry->eax, 0x1fU);
+		entry->eax = min(entry->eax, 0x24U);
 		break;
 	case 1:
 		cpuid_entry_override(entry, CPUID_1_EDX);
@@ -1174,6 +1178,28 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 			break;
 		}
 		break;
+	case 0x24: {
+		u8 avx10_version;
+
+		if (!kvm_cpu_cap_has(X86_FEATURE_AVX10)) {
+			entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
+			break;
+		}
+
+		/*
+		 * The AVX10 version is encoded in EBX[7:0].  Note, the version
+		 * is guaranteed to be >=1 if AVX10 is supported.  Note #2, the
+		 * version needs to be captured before overriding EBX features!
+		 */
+		avx10_version = min_t(u8, entry->ebx & 0xff, 1);
+		cpuid_entry_override(entry, CPUID_24_0_EBX);
+		entry->ebx |= avx10_version;
+
+		entry->eax = 0;
+		entry->ecx = 0;
+		entry->edx = 0;
+		break;
+	}
 	case KVM_CPUID_SIGNATURE: {
 		const u32 *sigptr = (const u32 *)KVM_SIGNATURE;
 		entry->eax = KVM_CPUID_FEATURES;

arch/x86/kvm/reverse_cpuid.h

@@ -17,6 +17,7 @@ enum kvm_only_cpuid_leafs {
 	CPUID_8000_0007_EDX,
 	CPUID_8000_0022_EAX,
 	CPUID_7_2_EDX,
+	CPUID_24_0_EBX,
 	NR_KVM_CPU_CAPS,
 
 	NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
@@ -46,6 +47,7 @@ enum kvm_only_cpuid_leafs {
 #define X86_FEATURE_AVX_NE_CONVERT      KVM_X86_FEATURE(CPUID_7_1_EDX, 5)
 #define X86_FEATURE_AMX_COMPLEX         KVM_X86_FEATURE(CPUID_7_1_EDX, 8)
 #define X86_FEATURE_PREFETCHITI         KVM_X86_FEATURE(CPUID_7_1_EDX, 14)
+#define X86_FEATURE_AVX10               KVM_X86_FEATURE(CPUID_7_1_EDX, 19)
 
 /* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */
 #define X86_FEATURE_INTEL_PSFD		KVM_X86_FEATURE(CPUID_7_2_EDX, 0)
@@ -55,6 +57,11 @@ enum kvm_only_cpuid_leafs {
 #define KVM_X86_FEATURE_BHI_CTRL	KVM_X86_FEATURE(CPUID_7_2_EDX, 4)
 #define X86_FEATURE_MCDT_NO		KVM_X86_FEATURE(CPUID_7_2_EDX, 5)
 
+/* Intel-defined sub-features, CPUID level 0x00000024:0 (EBX) */
+#define X86_FEATURE_AVX10_128		KVM_X86_FEATURE(CPUID_24_0_EBX, 16)
+#define X86_FEATURE_AVX10_256		KVM_X86_FEATURE(CPUID_24_0_EBX, 17)
+#define X86_FEATURE_AVX10_512		KVM_X86_FEATURE(CPUID_24_0_EBX, 18)
+
 /* CPUID level 0x80000007 (EDX). */
 #define KVM_X86_FEATURE_CONSTANT_TSC	KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8)
 
@@ -90,6 +97,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
 	[CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX},
 	[CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX},
 	[CPUID_7_2_EDX]       = {         7, 2, CPUID_EDX},
+	[CPUID_24_0_EBX]      = {      0x24, 0, CPUID_EBX},
 };
 
 /*