vdso, math64: Provide mul_u64_u32_add_u64_shr()

Provide mul_u64_u32_add_u64_shr() which is a calculation that will be used
by timekeeping and VDSO.

Place #include <vdso/math64.h> after #include <asm/div64.h> to allow
architecture-specific overrides, at least for the kernel.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20240325064023.2997-6-adrian.hunter@intel.com

Author: ahunter6

include/linux/math64.h

@@ -4,8 +4,8 @@
 
 #include <linux/types.h>
 #include <linux/math.h>
-#include <vdso/math64.h>
 #include <asm/div64.h>
+#include <vdso/math64.h>
 
 #if BITS_PER_LONG == 64
 

include/vdso/math64.h

@@ -21,4 +21,42 @@ __iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder)
 	return ret;
 }
 
+#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+
+#ifndef mul_u64_u32_add_u64_shr
+static __always_inline u64 mul_u64_u32_add_u64_shr(u64 a, u32 mul, u64 b, unsigned int shift)
+{
+	return (u64)((((unsigned __int128)a * mul) + b) >> shift);
+}
+#endif /* mul_u64_u32_add_u64_shr */
+
+#else
+
+#ifndef mul_u64_u32_add_u64_shr
+#ifndef mul_u32_u32
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+	return (u64)a * b;
+}
+#define mul_u32_u32 mul_u32_u32
+#endif
+static __always_inline u64 mul_u64_u32_add_u64_shr(u64 a, u32 mul, u64 b, unsigned int shift)
+{
+	u32 ah = a >> 32, al = a;
+	bool ovf;
+	u64 ret;
+
+	ovf = __builtin_add_overflow(mul_u32_u32(al, mul), b, &ret);
+	ret >>= shift;
+	if (ovf && shift)
+		ret += 1ULL << (64 - shift);
+	if (ah)
+		ret += mul_u32_u32(ah, mul) << (32 - shift);
+
+	return ret;
+}
+#endif /* mul_u64_u32_add_u64_shr */
+
+#endif
+
 #endif /* __VDSO_MATH64_H */