x86/math64: Provide a sane mul_u64_u32_div() implementation for x86_64

On x86_64 we can do a u64 * u64 -> u128 widening multiply followed by
a u128 / u64 -> u64 division to implement a sane version of
mul_u64_u32_div().
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/div64.h

@@ -73,6 +73,19 @@ static inline u64 mul_u32_u32(u32 a, u32 b)
 
 #else
 # include <asm-generic/div64.h>
+
+static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div)
+{
+	u64 q;
+
+	asm ("mulq %2; divq %3" : "=a" (q)
+				: "a" (a), "rm" ((u64)mul), "rm" ((u64)div)
+				: "rdx");
+
+	return q;
+}
+#define mul_u64_u32_div	mul_u64_u32_div
+
 #endif /* CONFIG_X86_32 */
 
 #endif /* _ASM_X86_DIV64_H */