1 files changed, 31 insertions, 8 deletions

diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h
index 9931e4c7d73f..30fd06ede751 100644
--- a/arch/x86/include/asm/div64.h
+++ b/arch/x86/include/asm/div64.h
@@ -60,6 +60,12 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
 }
 #define div_u64_rem	div_u64_rem
 
+/*
+ * gcc tends to zero extend 32bit values and do full 64bit maths.
+ * Define asm functions that avoid this.
+ * (clang generates better code for the C versions.)
+ */
+#ifndef __clang__
 static inline u64 mul_u32_u32(u32 a, u32 b)
 {
 	u32 high, low;
@@ -71,6 +77,19 @@ static inline u64 mul_u32_u32(u32 a, u32 b)
 }
 #define mul_u32_u32 mul_u32_u32
 
+static inline u64 add_u64_u32(u64 a, u32 b)
+{
+	u32 high = a >> 32, low = a;
+
+	asm ("addl %[b], %[low]; adcl $0, %[high]"
+		: [low] "+r" (low), [high] "+r" (high)
+		: [b] "rm" (b) );
+
+	return low | (u64)high << 32;
+}
+#define add_u64_u32 add_u64_u32
+#endif
+
 /*
  * __div64_32() is never called on x86, so prevent the
  * generic definition from getting built.
@@ -84,21 +103,25 @@ static inline u64 mul_u32_u32(u32 a, u32 b)
  * Will generate an #DE when the result doesn't fit u64, could fix with an
  * __ex_table[] entry when it becomes an issue.
  */
-static inline u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div)
+static inline u64 mul_u64_add_u64_div_u64(u64 rax, u64 mul, u64 add, u64 div)
 {
-	u64 q;
+	u64 rdx;
+
+	asm ("mulq %[mul]" : "+a" (rax), "=d" (rdx) : [mul] "rm" (mul));
+
+	if (!statically_true(!add))
+		asm ("addq %[add], %[lo]; adcq $0, %[hi]" :
+			[lo] "+r" (rax), [hi] "+r" (rdx) : [add] "irm" (add));
 
-	asm ("mulq %2; divq %3" : "=a" (q)
-				: "a" (a), "rm" (mul), "rm" (div)
-				: "rdx");
+	asm ("divq %[div]" : "+a" (rax), "+d" (rdx) : [div] "rm" (div));
 
-	return q;
+	return rax;
 }
-#define mul_u64_u64_div_u64 mul_u64_u64_div_u64
+#define mul_u64_add_u64_div_u64 mul_u64_add_u64_div_u64
 
 static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div)
 {
-	return mul_u64_u64_div_u64(a, mul, div);
+	return mul_u64_add_u64_div_u64(a, mul, 0, div);
 }
 #define mul_u64_u32_div	mul_u64_u32_div