math64: New separate div64_u64_rem helper

Commit f792685006274a850e6cc0ea9ade275ccdfc90bc ("math64: New
div64_u64_rem helper") implemented div64_u64 in terms of div64_u64_rem.
But div64_u64_rem was removed because it slowed down div64_u64 (and
there were no other users of div64_u64_rem).

Device Mapper's I/O statistics support has a need for div64_u64_rem;
reintroduce this helper as a separate method that doesn't slow down
div64_u64, especially on 32-bit systems.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
diff --git a/lib/div64.c b/lib/div64.c
index a163b6c..4382ad7 100644
--- a/lib/div64.c
+++ b/lib/div64.c
@@ -79,6 +79,46 @@
 #endif
 
 /**
+ * div64_u64_rem - unsigned 64bit divide with 64bit divisor and remainder
+ * @dividend:	64bit dividend
+ * @divisor:	64bit divisor
+ * @remainder:  64bit remainder
+ *
+ * This implementation is a comparable to algorithm used by div64_u64.
+ * But this operation, which includes math for calculating the remainder,
+ * is kept distinct to avoid slowing down the div64_u64 operation on 32bit
+ * systems.
+ */
+#ifndef div64_u64_rem
+u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder)
+{
+	u32 high = divisor >> 32;
+	u64 quot;
+
+	if (high == 0) {
+		u32 rem32;
+		quot = div_u64_rem(dividend, divisor, &rem32);
+		*remainder = rem32;
+	} else {
+		int n = 1 + fls(high);
+		quot = div_u64(dividend >> n, divisor >> n);
+
+		if (quot != 0)
+			quot--;
+
+		*remainder = dividend - quot * divisor;
+		if (*remainder >= divisor) {
+			quot++;
+			*remainder -= divisor;
+		}
+	}
+
+	return quot;
+}
+EXPORT_SYMBOL(div64_u64_rem);
+#endif
+
+/**
  * div64_u64 - unsigned 64bit divide with 64bit divisor
  * @dividend:	64bit dividend
  * @divisor:	64bit divisor