diff --git a/litex/soc/software/bios/boot.c b/litex/soc/software/bios/boot.c
index 786039f0e..20953e711 100644
--- a/litex/soc/software/bios/boot.c
+++ b/litex/soc/software/bios/boot.c
@@ -23,6 +23,7 @@
 #include "sfl.h"
 #include "boot.h"
 
+#include <progress.h>
 #include <spiflash.h>
 
 #include <libliteeth/udp.h>
diff --git a/litex/soc/software/include/base/div64.h b/litex/soc/software/include/base/div64.h
new file mode 100644
index 000000000..2f0754746
--- /dev/null
+++ b/litex/soc/software/include/base/div64.h
@@ -0,0 +1,39 @@
+#ifndef _ASM_GENERIC_DIV64_H
+#define _ASM_GENERIC_DIV64_H
+/*
+ * Copyright (C) 2003 Bernardo Innocenti <bernie@develer.com>
+ * Based on former asm-ppc/div64.h and asm-m68knommu/div64.h
+ *
+ * The semantics of do_div() are:
+ *
+ * uint32_t do_div(uint64_t *n, uint32_t base)
+ * {
+ * 	uint32_t remainder = *n % base;
+ * 	*n = *n / base;
+ * 	return remainder;
+ * }
+ *
+ * NOTE: macro parameter n is evaluated multiple times,
+ *       beware of side effects!
+ */
+
+#include <stdint.h>
+
+extern uint32_t __div64_32(uint64_t *dividend, uint32_t divisor);
+
+/* The unnecessary pointer compare is there
+ * to check for type safety (n must be 64bit)
+ */
+# define do_div(n,base) ({				\
+	uint32_t __base = (base);			\
+	uint32_t __rem;					\
+	(void)(((typeof((n)) *)0) == ((uint64_t *)0));	\
+	if (((n) >> 32) == 0) {			\
+		__rem = (uint32_t)(n) % __base;		\
+		(n) = (uint32_t)(n) / __base;		\
+	} else 						\
+		__rem = __div64_32(&(n), __base);	\
+	__rem;						\
+ })
+
+#endif /* _ASM_GENERIC_DIV64_H */
diff --git a/litex/soc/software/libbase/Makefile b/litex/soc/software/libbase/Makefile
index 107c87364..5974e0007 100755
--- a/litex/soc/software/libbase/Makefile
+++ b/litex/soc/software/libbase/Makefile
@@ -3,7 +3,7 @@ include $(SOC_DIRECTORY)/software/common.mak
 
 OBJECTS = exception.o libc.o errno.o crc16.o crc32.o console.o \
 	system.o id.o uart.o time.o qsort.o strtod.o spiflash.o strcasecmp.o i2c.o \
-	progress.o
+	div64.o progress.o
 
 all: crt0-ctr.o crt0-xip.o libbase.a libbase-nofloat.a
 
diff --git a/litex/soc/software/libbase/div64.c b/litex/soc/software/libbase/div64.c
new file mode 100644
index 000000000..98d77480d
--- /dev/null
+++ b/litex/soc/software/libbase/div64.c
@@ -0,0 +1,54 @@
+/*
+ * Copyright (C) 2003 Bernardo Innocenti <bernie@develer.com>
+ *
+ * Based on former do_div() implementation from asm-parisc/div64.h:
+ *	Copyright (C) 1999 Hewlett-Packard Co
+ *	Copyright (C) 1999 David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ *
+ * Generic C version of 64bit/32bit division and modulo, with
+ * 64bit result and 32bit remainder.
+ *
+ * The fast case for (n>>32 == 0) is handled inline by do_div().
+ *
+ * Code generated for this function might be very inefficient
+ * for some CPUs. __div64_32() can be overridden by linking arch-specific
+ * assembly versions such as arch/ppc/lib/div64.S and arch/sh/lib/div64.S.
+ */
+
+#include <stdint.h>
+
+#include <div64.h>
+
+uint32_t __div64_32(uint64_t *n, uint32_t base)
+{
+	uint64_t rem = *n;
+	uint64_t b = base;
+	uint64_t res, d = 1;
+	uint32_t high = rem >> 32;
+
+	/* Reduce the thing a bit first */
+	res = 0;
+	if (high >= base) {
+		high /= base;
+		res = (uint64_t) high << 32;
+		rem -= (uint64_t) (high*base) << 32;
+	}
+
+	while ((int64_t)b > 0 && b < rem) {
+		b = b+b;
+		d = d+d;
+	}
+
+	do {
+		if (rem >= b) {
+			rem -= b;
+			res += d;
+		}
+		b >>= 1;
+		d >>= 1;
+	} while (d);
+
+	*n = res;
+	return rem;
+}
diff --git a/litex/soc/software/libbase/progress.c b/litex/soc/software/libbase/progress.c
index c13b2dad4..d8521fce0 100644
--- a/litex/soc/software/libbase/progress.c
+++ b/litex/soc/software/libbase/progress.c
@@ -20,6 +20,8 @@
 #include <console.h>
 #include <stdio.h>
 #include <stdint.h>
+
+#include <div64.h>
 #include <progress.h>
 
 #define FILESIZE_MAX    100000000
@@ -29,56 +31,6 @@ static int printed;
 static int progress_max;
 static int spin;
 
-uint32_t __div64_32(uint64_t *n, uint32_t base)
-{
-	uint64_t rem = *n;
-	uint64_t b = base;
-	uint64_t res, d = 1;
-	uint32_t high = rem >> 32;
-
-	/* Reduce the thing a bit first */
-	res = 0;
-	if (high >= base) {
-		high /= base;
-		res = (uint64_t) high << 32;
-		rem -= (uint64_t) (high*base) << 32;
-	}
-
-	while ((int64_t)b > 0 && b < rem) {
-		b = b+b;
-		d = d+d;
-	}
-
-	do {
-		if (rem >= b) {
-			rem -= b;
-			res += d;
-		}
-		b >>= 1;
-		d >>= 1;
-	} while (d);
-
-	*n = res;
-	return rem;
-}
-
-
-/* The unnecessary pointer compare is there
- * to check for type safety (n must be 64bit)
- */
-# define do_div(n,base) ({				\
-	uint32_t __base = (base);			\
-	uint32_t __rem;					\
-	(void)(((typeof((n)) *)0) == ((uint64_t *)0));	\
-	if (((n) >> 32) == 0) {			\
-		__rem = (uint32_t)(n) % __base;		\
-		(n) = (uint32_t)(n) / __base;		\
-	} else 						\
-		__rem = __div64_32(&(n), __base);	\
-	__rem;						\
- })
-
-
 void show_progress(int now)
 {
 	char spinchr[] = "\\|/-";