sh: math-emu support

This implements initial math-emu support, aimed primarily at SH-3.

Signed-off-by: Takashi YOSHII <takasi-y@ops.dti.ne.jp>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
diff --git a/arch/sh/math-emu/sfp-util.h b/arch/sh/math-emu/sfp-util.h
new file mode 100644
index 0000000..8ae1bd3
--- /dev/null
+++ b/arch/sh/math-emu/sfp-util.h
@@ -0,0 +1,72 @@
+/*
+ * These are copied from glibc/stdlib/longlong.h
+ */
+
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  do {                                                                  \
+    UWtype __x;                                                         \
+    __x = (al) + (bl);                                                  \
+    (sh) = (ah) + (bh) + (__x < (al));                                  \
+    (sl) = __x;                                                         \
+  } while (0)
+
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  do {                                                                  \
+    UWtype __x;                                                         \
+    __x = (al) - (bl);                                                  \
+    (sh) = (ah) - (bh) - (__x > (al));                                  \
+    (sl) = __x;                                                         \
+  } while (0)
+
+#define umul_ppmm(w1, w0, u, v) \
+  __asm__ ("dmulu.l %2,%3\n\tsts    macl,%1\n\tsts  mach,%0"	\
+	: "=r" ((u32)(w1)), "=r" ((u32)(w0))	\
+	:  "r" ((u32)(u)),   "r" ((u32)(v))	\
+	: "macl", "mach")
+
+#define __ll_B ((UWtype) 1 << (W_TYPE_SIZE / 2))
+#define __ll_lowpart(t) ((UWtype) (t) & (__ll_B - 1))
+#define __ll_highpart(t) ((UWtype) (t) >> (W_TYPE_SIZE / 2))
+
+#define udiv_qrnnd(q, r, n1, n0, d) \
+  do {									\
+    UWtype __d1, __d0, __q1, __q0;					\
+    UWtype __r1, __r0, __m;						\
+    __d1 = __ll_highpart (d);						\
+    __d0 = __ll_lowpart (d);						\
+									\
+    __r1 = (n1) % __d1;							\
+    __q1 = (n1) / __d1;							\
+    __m = (UWtype) __q1 * __d0;						\
+    __r1 = __r1 * __ll_B | __ll_highpart (n0);				\
+    if (__r1 < __m)							\
+      {									\
+	__q1--, __r1 += (d);						\
+	if (__r1 >= (d)) /* i.e. we didn't get carry when adding to __r1 */\
+	  if (__r1 < __m)						\
+	    __q1--, __r1 += (d);					\
+      }									\
+    __r1 -= __m;							\
+									\
+    __r0 = __r1 % __d1;							\
+    __q0 = __r1 / __d1;							\
+    __m = (UWtype) __q0 * __d0;						\
+    __r0 = __r0 * __ll_B | __ll_lowpart (n0);				\
+    if (__r0 < __m)							\
+      {									\
+	__q0--, __r0 += (d);						\
+	if (__r0 >= (d))						\
+	  if (__r0 < __m)						\
+	    __q0--, __r0 += (d);					\
+      }									\
+    __r0 -= __m;							\
+									\
+    (q) = (UWtype) __q1 * __ll_B | __q0;				\
+    (r) = __r0;								\
+  } while (0)
+
+#define abort()	return 0
+
+#define __BYTE_ORDER __LITTLE_ENDIAN
+
+