tools include: Add an initial math64.h

Add an initial math64.h similar to linux/math64.h with functions
mul_u64_u64_div64() and mul_u64_u32_shr(). This isn't a direct copy of
include/linux/math64.h as that doesn't define mul_u64_u64_div64().

Implementation was written by Peter Zilkstra based on linux/math64.h
and div64.h[1]. The original implementation was not optimal on arm64 as
__int128 division is not optimal with a call out to __udivti3, so I
dropped the __int128 variant of mul_u64_u64_div64().

[1] https://lore.kernel.org/lkml/20200322101848.GF2452@worktop.programming.kicks-ass.net/Signed-off-by: Rob Herring <robh@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Itaru Kitayama <itaru.kitayama@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Link: http://lore.kernel.org/lkml/20210414155412.3697605-2-robh@kernel.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/include/linux/math64.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_MATH64_H
+#define _LINUX_MATH64_H
+
+#include <linux/types.h>
+
+#ifdef __x86_64__
+static inline u64 mul_u64_u64_div64(u64 a, u64 b, u64 c)
+{
+	u64 q;
+
+	asm ("mulq %2; divq %3" : "=a" (q)
+				: "a" (a), "rm" (b), "rm" (c)
+				: "rdx");
+
+	return q;
+}
+#define mul_u64_u64_div64 mul_u64_u64_div64
+#endif
+
+#ifdef __SIZEOF_INT128__
+static inline u64 mul_u64_u32_shr(u64 a, u32 b, unsigned int shift)
+{
+	return (u64)(((unsigned __int128)a * b) >> shift);
+}
+
+#else
+
+#ifdef __i386__
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+	u32 high, low;
+
+	asm ("mull %[b]" : "=a" (low), "=d" (high)
+			 : [a] "a" (a), [b] "rm" (b) );
+
+	return low | ((u64)high) << 32;
+}
+#else
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+	return (u64)a * b;
+}
+#endif
+
+static inline u64 mul_u64_u32_shr(u64 a, u32 b, unsigned int shift)
+{
+	u32 ah, al;
+	u64 ret;
+
+	al = a;
+	ah = a >> 32;
+
+	ret = mul_u32_u32(al, b) >> shift;
+	if (ah)
+		ret += mul_u32_u32(ah, b) << (32 - shift);
+
+	return ret;
+}
+
+#endif	/* __SIZEOF_INT128__ */
+
+#ifndef mul_u64_u64_div64
+static inline u64 mul_u64_u64_div64(u64 a, u64 b, u64 c)
+{
+	u64 quot, rem;
+
+	quot = a / c;
+	rem = a % c;
+
+	return quot * b + (rem * b) / c;
+}
+#endif
+
+#endif /* _LINUX_MATH64_H */