x86/cpufeatures: Enumerate the new AVX512 BFLOAT16 instructions

AVX512 BFLOAT16 instructions support 16-bit BFLOAT16 floating-point
format (BF16) for deep learning optimization.

BF16 is a short version of 32-bit single-precision floating-point
format (FP32) and has several advantages over 16-bit half-precision
floating-point format (FP16). BF16 keeps FP32 accumulation after
multiplication without loss of precision, offers more than enough
range for deep learning training tasks, and doesn't need to handle
hardware exception.

AVX512 BFLOAT16 instructions are enumerated in CPUID.7.1:EAX[bit 5]
AVX512_BF16.

CPUID.7.1:EAX contains only feature bits. Reuse the currently empty
word 12 as a pure features word to hold the feature bits including
AVX512_BF16.

Detailed information of the CPUID bit and AVX512 BFLOAT16 instructions
can be found in the latest Intel Architecture Instruction Set Extensions
and Future Features Programming Reference.

 [ bp: Check CPUID(7) subleaf validity before accessing subleaf 1. ]
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: "Chang S. Bae" <chang.seok.bae@intel.com>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nadav Amit <namit@vmware.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Pavel Tatashin <pasha.tatashin@oracle.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: Radim Krcmar <rkrcmar@redhat.com>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: "Ravi V Shankar" <ravi.v.shankar@intel.com>
Cc: Robert Hoo <robert.hu@linux.intel.com>
Cc: "Sean J Christopherson" <sean.j.christopherson@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Lendacky <Thomas.Lendacky@amd.com>
Cc: x86 <x86@kernel.org>
Link: https://lkml.kernel.org/r/1560794416-217638-3-git-send-email-fenghua.yu@intel.com

arch/x86/include/asm/cpufeature.h

@@ -23,7 +23,7 @@ enum cpuid_leafs
 	CPUID_7_0_EBX,
 	CPUID_D_1_EAX,
 	CPUID_LNX_4,
-	CPUID_DUMMY,
+	CPUID_7_1_EAX,
 	CPUID_8000_0008_EBX,
 	CPUID_6_EAX,
 	CPUID_8000_000A_EDX,

arch/x86/include/asm/cpufeatures.h

@@ -282,6 +282,9 @@
 #define X86_FEATURE_CQM_MBM_TOTAL	(11*32+ 2) /* LLC Total MBM monitoring */
 #define X86_FEATURE_CQM_MBM_LOCAL	(11*32+ 3) /* LLC Local MBM monitoring */
 
+/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
+
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */

arch/x86/kernel/cpu/common.c

@@ -847,6 +847,12 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_7_0_EBX] = ebx;
 		c->x86_capability[CPUID_7_ECX] = ecx;
 		c->x86_capability[CPUID_7_EDX] = edx;
+
+		/* Check valid sub-leaf index before accessing it */
+		if (eax >= 1) {
+			cpuid_count(0x00000007, 1, &eax, &ebx, &ecx, &edx);
+			c->x86_capability[CPUID_7_1_EAX] = eax;
+		}
 	}
 
 	/* Extended state features: level 0x0000000d */

arch/x86/kernel/cpu/cpuid-deps.c

@@ -62,6 +62,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_CQM_OCCUP_LLC,	X86_FEATURE_CQM_LLC   },
 	{ X86_FEATURE_CQM_MBM_TOTAL,	X86_FEATURE_CQM_LLC   },
 	{ X86_FEATURE_CQM_MBM_LOCAL,	X86_FEATURE_CQM_LLC   },
+	{ X86_FEATURE_AVX512_BF16,	X86_FEATURE_AVX512VL  },
 	{}
 };