[PATCH V4 06/14] x86/math64: Provide a sane mul_u64_u32_div() implementation for x86_64

[kan . liang]

From: "Peter Zijlstra (Intel)" <peterz@xxxxxxxxxxxxx>

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@xxxxxxxxxxxxx>
---

New patch for V4

 arch/x86/include/asm/div64.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h
index 20a46150e0a8..9b8cb50768c2 100644
--- a/arch/x86/include/asm/div64.h
+++ b/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 */
-- 
2.17.1