math64: Add mul_u64_u32_shr()

Introduce mul_u64_u32_shr() as proposed by Andy a while back; it
allows using 64x64->128 muls on 64bit archs and recent GCC
which defines __SIZEOF_INT128__ and __int128.

(This new method will be used by the scheduler.)

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: fweisbec@gmail.com
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-hxjoeuzmrcaumR0uZwjpe2pv@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/Kconfig

@@ -26,6 +26,7 @@ config X86
 	select HAVE_AOUT if X86_32
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select ARCH_SUPPORTS_NUMA_BALANCING
+	select ARCH_SUPPORTS_INT128 if X86_64
 	select ARCH_WANTS_PROT_NUMA_PROT_NONE
 	select HAVE_IDE
 	select HAVE_OPROFILE

include/linux/math64.h

@@ -133,4 +133,34 @@ __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_shr
+static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift)
+{
+	return (u64)(((unsigned __int128)a * mul) >> shift);
+}
+#endif /* mul_u64_u32_shr */
+
+#else
+
+#ifndef mul_u64_u32_shr
+static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift)
+{
+	u32 ah, al;
+	u64 ret;
+
+	al = a;
+	ah = a >> 32;
+
+	ret = ((u64)al * mul) >> shift;
+	if (ah)
+		ret += ((u64)ah * mul) << (32 - shift);
+
+	return ret;
+}
+#endif /* mul_u64_u32_shr */
+
+#endif
+
 #endif /* _LINUX_MATH64_H */

init/Kconfig

@@ -809,6 +809,12 @@ config GENERIC_SCHED_CLOCK
 config ARCH_SUPPORTS_NUMA_BALANCING
 	bool
 
+#
+# For architectures that know their GCC __int128 support is sound
+#
+config ARCH_SUPPORTS_INT128
+	bool
+
 # For architectures that (ab)use NUMA to represent different memory regions
 # all cpu-local but of different latencies, such as SuperH.
 #