introduce explicit signed/unsigned 64bit divide

The current do_div doesn't explicitly say that it's unsigned and the signed
counterpart is missing, which is e.g.  needed when dealing with time values.

This introduces 64bit signed/unsigned divide functions which also attempts to
cleanup the somewhat awkward calling API, which often requires the use of
temporary variables for the dividend.  To avoid the need for temporary
variables everywhere for the remainder, each divide variant also provides a
version which doesn't return the remainder.

Each architecture can now provide optimized versions of these function,
otherwise generic fallback implementations will be used.

As an example I provided an alternative for the current x86 divide, which
avoids the asm casts and using an union allows gcc to generate better code.
It also avoids the upper divde in a few more cases, where the result is known
(i.e.  upper quotient is zero).

Signed-off-by: Roman Zippel <zippel@linux-m68k.org>
Cc: john stultz <johnstul@us.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 113 insertions, 2 deletions

diff --git a/include/asm-x86/div64.h b/include/asm-x86/div64.h
index 0dbf8bf3ef0a8..c7892cfe9ce65 100644
--- a/include/asm-x86/div64.h
+++ b/include/asm-x86/div64.h
@@ -51,6 +51,26 @@ static inline long div_ll_X_l_rem(long long divs, long div, long *rem)
 
 }
 
+static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
+{
+	union {
+		u64 v64;
+		u32 v32[2];
+	} d = { dividend };
+	u32 upper;
+
+	upper = d.v32[1];
+	d.v32[1] = 0;
+	if (upper >= divisor) {
+		d.v32[1] = upper / divisor;
+		upper %= divisor;
+	}
+	asm ("divl %2" : "=a" (d.v32[0]), "=d" (*remainder) :
+		"rm" (divisor), "0" (d.v32[0]), "1" (upper));
+	return d.v64;
+}
+#define div_u64_rem	div_u64_rem
+
 extern uint64_t div64_64(uint64_t dividend, uint64_t divisor);
 
 #else
diff --git a/include/linux/math64.h b/include/linux/math64.h
new file mode 100644
index 0000000000000..6d17166410085
--- /dev/null
+++ b/include/linux/math64.h
@@ -0,0 +1,72 @@
+#ifndef _LINUX_MATH64_H
+#define _LINUX_MATH64_H
+
+#include <linux/types.h>
+#include <asm/div64.h>
+
+#if BITS_PER_LONG == 64
+
+/**
+ * div_u64_rem - unsigned 64bit divide with 32bit divisor with remainder
+ *
+ * This is commonly provided by 32bit archs to provide an optimized 64bit
+ * divide.
+ */
+static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
+{
+	*remainder = dividend % divisor;
+	return dividend / divisor;
+}
+
+/**
+ * div_s64_rem - signed 64bit divide with 32bit divisor with remainder
+ */
+static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder)
+{
+	*remainder = dividend % divisor;
+	return dividend / divisor;
+}
+
+#elif BITS_PER_LONG == 32
+
+#ifndef div_u64_rem
+static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
+{
+	*remainder = do_div(dividend, divisor);
+	return dividend;
+}
+#endif
+
+#ifndef div_s64_rem
+extern s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder);
+#endif
+
+#endif /* BITS_PER_LONG */
+
+/**
+ * div_u64 - unsigned 64bit divide with 32bit divisor
+ *
+ * This is the most common 64bit divide and should be used if possible,
+ * as many 32bit archs can optimize this variant better than a full 64bit
+ * divide.
+ */
+#ifndef div_u64
+static inline u64 div_u64(u64 dividend, u32 divisor)
+{
+	u32 remainder;
+	return div_u64_rem(dividend, divisor, &remainder);
+}
+#endif
+
+/**
+ * div_s64 - signed 64bit divide with 32bit divisor
+ */
+#ifndef div_s64
+static inline s64 div_s64(s64 dividend, s32 divisor)
+{
+	s32 remainder;
+	return div_s64_rem(dividend, divisor, &remainder);
+}
+#endif
+
+#endif /* _LINUX_MATH64_H */
diff --git a/lib/div64.c b/lib/div64.c
index b71cf93c529ad..689bd76833faf 100644
--- a/lib/div64.c
+++ b/lib/div64.c
@@ -16,9 +16,8 @@
  * assembly versions such as arch/ppc/lib/div64.S and arch/sh/lib/div64.S.
  */
 
-#include <linux/types.h>
 #include <linux/module.h>
-#include <asm/div64.h>
+#include <linux/math64.h>
 
 /* Not needed on 64bit architectures */
 #if BITS_PER_LONG == 32
@@ -58,6 +57,26 @@ uint32_t __attribute__((weak)) __div64_32(uint64_t *n, uint32_t base)
 
 EXPORT_SYMBOL(__div64_32);
 
+#ifndef div_s64_rem
+s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder)
+{
+	u64 quotient;
+
+	if (dividend < 0) {
+		quotient = div_u64_rem(-dividend, abs(divisor), (u32 *)remainder);
+		*remainder = -*remainder;
+		if (divisor > 0)
+			quotient = -quotient;
+	} else {
+		quotient = div_u64_rem(dividend, abs(divisor), (u32 *)remainder);
+		if (divisor < 0)
+			quotient = -quotient;
+	}
+	return quotient;
+}
+EXPORT_SYMBOL(div_s64_rem);
+#endif
+
 /* 64bit divisor, dividend and result. dynamic precision */
 uint64_t div64_64(uint64_t dividend, uint64_t divisor)
 {