[U-Boot] [PATCH] nios2: fix r15 issue for gcc4

[U-Boot] [PATCH] nios2: fix r15 issue for gcc4

[Thomas Chou]

The "-ffixed-r15" option doesn't work well for gcc4. Since we
don't use gp for small data with option "-G0", we can use gp
as global data pointer. This allows compiler to use r15. It
is necessary for gcc4 to work properly.

Signed-off-by: Thomas Chou <thomas@wytron.com.tw>
---
 arch/nios2/config.mk                 |    2 +-
 arch/nios2/cpu/start.S               |    7 -------
 arch/nios2/include/asm/global_data.h |    2 +-
 3 files changed, 2 insertions(+), 9 deletions(-)

diff --git a/arch/nios2/config.mk b/arch/nios2/config.mk
index 8e5d6ef..6789038 100644
--- a/arch/nios2/config.mk
+++ b/arch/nios2/config.mk
@@ -27,6 +27,6 @@ CROSS_COMPILE ?= nios2-elf-
 STANDALONE_LOAD_ADDR = 0x02000000 -L $(gcclibdir)
 
 PLATFORM_CPPFLAGS += -DCONFIG_NIOS2 -D__NIOS2__
-PLATFORM_CPPFLAGS += -ffixed-r15 -G0
+PLATFORM_CPPFLAGS += -G0
 
 LDSCRIPT ?= $(SRCTREE)/$(CPUDIR)/u-boot.lds
diff --git a/arch/nios2/cpu/start.S b/arch/nios2/cpu/start.S
index d1016ea..76d3b52 100644
--- a/arch/nios2/cpu/start.S
+++ b/arch/nios2/cpu/start.S
@@ -113,13 +113,6 @@ _cur:	movhi	r5, %hi(_cur - _start)
 	 bne	r5, r6, 4b
 5:
 
-	/* GLOBAL POINTER -- the global pointer is used to reference
-	 * "small data" (see -G switch). The linker script must
-	 * provide the gp address.
-	 */
-	 movhi	gp, %hi(_gp)
-	 ori	gp, gp, %lo(_gp)
-
 	/* JUMP TO RELOC ADDR */
 	movhi	r4, %hi(_reloc)
 	ori	r4, r4, %lo(_reloc)
diff --git a/arch/nios2/include/asm/global_data.h b/arch/nios2/include/asm/global_data.h
index 34aa962..f1b3482 100644
--- a/arch/nios2/include/asm/global_data.h
+++ b/arch/nios2/include/asm/global_data.h
@@ -48,6 +48,6 @@ typedef	struct	global_data {
 #define	GD_FLG_LOGINIT	0x00020		/* Log Buffer has been initialized	*/
 #define GD_FLG_DISABLE_CONSOLE	0x00040		/* Disable console (in & out)	 */
 
-#define DECLARE_GLOBAL_DATA_PTR     register gd_t *gd asm ("r15")
+#define DECLARE_GLOBAL_DATA_PTR     register gd_t *gd asm ("gp")
 
 #endif /* __ASM_NIOS2_GLOBALDATA_H_ */
-- 
1.5.5.6

[U-Boot] [PATCH] nios2: fix div64 issue for gcc4

[Thomas Chou]

This patch fixes the run-time error on div64 when built with
gcc4, which was reported by jhwu0625 on nios forum. It merges
math support from libgcc of gcc4. This patch is copied from
nios2-linux.

It works with both gcc3 and gcc4. The old mult.c, divmod.c and
math.h are removed.

Signed-off-by: Thomas Chou <thomas@wytron.com.tw>
---
 arch/nios2/lib/Makefile   |    3 +-
 arch/nios2/lib/divmod.c   |  101 --------
 arch/nios2/lib/libgcc.c   |  592 +++++++++++++++++++++++++++++++++++++++++++++
 arch/nios2/lib/longlong.h |  263 ++++++++++++++++++++
 arch/nios2/lib/math.h     |   16 --
 arch/nios2/lib/mult.c     |   56 -----
 6 files changed, 856 insertions(+), 175 deletions(-)
 delete mode 100644 arch/nios2/lib/divmod.c
 create mode 100644 arch/nios2/lib/libgcc.c
 create mode 100644 arch/nios2/lib/longlong.h
 delete mode 100644 arch/nios2/lib/math.h
 delete mode 100644 arch/nios2/lib/mult.c

diff --git a/arch/nios2/lib/Makefile b/arch/nios2/lib/Makefile
index b69bc38..92320c5 100644
--- a/arch/nios2/lib/Makefile
+++ b/arch/nios2/lib/Makefile
@@ -29,8 +29,7 @@ SOBJS-y	+= cache.o
 
 COBJS-y	+= board.o
 COBJS-y	+= bootm.o
-COBJS-y	+= divmod.o
-COBJS-y	+= mult.o
+COBJS-y	+= libgcc.o
 COBJS-y	+= time.o
 
 SRCS	:= $(SOBJS-y:.o=.S) $(COBJS-y:.o=.c)
diff --git a/arch/nios2/lib/divmod.c b/arch/nios2/lib/divmod.c
deleted file mode 100644
index 3c7e71e..0000000
--- a/arch/nios2/lib/divmod.c
+++ /dev/null
@@ -1,101 +0,0 @@
-/*
- * This file is part of GNU CC.
- *
- * GNU CC is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published
- * by the Free Software Foundation; either version 2, or (at your
- * option) any later version.
- *
- * GNU CC is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public
- * License along with GNU CC; see the file COPYING.  If not, write
- * to the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
- */
-
-
-#include "math.h"
-
-USItype udivmodsi4 (USItype num, USItype den, word_type modwanted)
-{
-	USItype bit = 1;
-	USItype res = 0;
-
-	while (den < num && bit && !(den & (1L << 31))) {
-		den <<= 1;
-		bit <<= 1;
-	}
-	while (bit) {
-		if (num >= den) {
-			num -= den;
-			res |= bit;
-		}
-		bit >>= 1;
-		den >>= 1;
-	}
-	if (modwanted)
-		return num;
-	return res;
-}
-
-
-SItype __divsi3 (SItype a, SItype b)
-{
-	word_type neg = 0;
-	SItype res;
-
-	if (a < 0) {
-		a = -a;
-		neg = !neg;
-	}
-
-	if (b < 0) {
-		b = -b;
-		neg = !neg;
-	}
-
-	res = udivmodsi4 (a, b, 0);
-
-	if (neg)
-		res = -res;
-
-	return res;
-}
-
-
-SItype __modsi3 (SItype a, SItype b)
-{
-	word_type neg = 0;
-	SItype res;
-
-	if (a < 0) {
-		a = -a;
-		neg = 1;
-	}
-
-	if (b < 0)
-		b = -b;
-
-	res = udivmodsi4 (a, b, 1);
-
-	if (neg)
-		res = -res;
-
-	return res;
-}
-
-
-SItype __udivsi3 (SItype a, SItype b)
-{
-	return udivmodsi4 (a, b, 0);
-}
-
-
-SItype __umodsi3 (SItype a, SItype b)
-{
-	return udivmodsi4 (a, b, 1);
-}
diff --git a/arch/nios2/lib/libgcc.c b/arch/nios2/lib/libgcc.c
new file mode 100644
index 0000000..dc05627
--- /dev/null
+++ b/arch/nios2/lib/libgcc.c
@@ -0,0 +1,592 @@
+/*
+ * This file is part of GNU CC.
+ *
+ * GNU CC is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published
+ * by the Free Software Foundation; either version 2, or (at your
+ * option) any later version.
+ *
+ * GNU CC is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with GNU CC; see the file COPYING.  If not, write
+ * to the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ */
+
+typedef unsigned int UWtype;
+typedef unsigned int UHWtype;
+typedef unsigned long long UDWtype;
+#define W_TYPE_SIZE 32
+
+typedef unsigned char UQItype;
+typedef long SItype;
+typedef unsigned long USItype;
+typedef long long DItype;
+typedef unsigned long long DSItype;
+
+#include "longlong.h"
+
+
+typedef int word_type;
+typedef long Wtype;
+typedef long long DWtype;
+
+struct DWstruct { Wtype low, high;};
+
+typedef union
+{
+  struct DWstruct s;
+  DWtype ll;
+} DWunion;
+
+#define BITS_PER_UNIT 8
+
+UDWtype
+__udivmoddi4 (UDWtype n, UDWtype d, UDWtype *rp);
+
+const UQItype __clz_tab[256] =
+{
+  0,1,2,2,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,
+  6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,
+  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
+  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
+  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
+  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
+  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
+  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8
+};
+
+
+DWtype
+__ashldi3 (DWtype u, word_type b)
+{
+  if (b == 0)
+    return u;
+
+  const DWunion uu = {.ll = u};
+  const word_type bm = (sizeof (Wtype) * BITS_PER_UNIT) - b;
+  DWunion w;
+
+  if (bm <= 0)
+    {
+      w.s.low = 0;
+      w.s.high = (UWtype) uu.s.low << -bm;
+    }
+  else
+    {
+      const UWtype carries = (UWtype) uu.s.low >> bm;
+
+      w.s.low = (UWtype) uu.s.low << b;
+      w.s.high = ((UWtype) uu.s.high << b) | carries;
+    }
+
+  return w.ll;
+}
+
+DWtype
+__ashrdi3 (DWtype u, word_type b)
+{
+  if (b == 0)
+    return u;
+
+  const DWunion uu = {.ll = u};
+  const word_type bm = (sizeof (Wtype) * BITS_PER_UNIT) - b;
+  DWunion w;
+
+  if (bm <= 0)
+    {
+      /* w.s.high = 1..1 or 0..0 */
+      w.s.high = uu.s.high >> (sizeof (Wtype) * BITS_PER_UNIT - 1);
+      w.s.low = uu.s.high >> -bm;
+    }
+  else
+    {
+      const UWtype carries = (UWtype) uu.s.high << bm;
+
+      w.s.high = uu.s.high >> b;
+      w.s.low = ((UWtype) uu.s.low >> b) | carries;
+    }
+
+  return w.ll;
+}
+
+DWtype
+__lshrdi3 (DWtype u, word_type b)
+{
+  if (b == 0)
+    return u;
+
+  const DWunion uu = {.ll = u};
+  const word_type bm = (sizeof (Wtype) * BITS_PER_UNIT) - b;
+  DWunion w;
+
+  if (bm <= 0)
+    {
+      w.s.high = 0;
+      w.s.low = (UWtype) uu.s.high >> -bm;
+    }
+  else
+    {
+      const UWtype carries = (UWtype) uu.s.high << bm;
+
+      w.s.high = (UWtype) uu.s.high >> b;
+      w.s.low = ((UWtype) uu.s.low >> b) | carries;
+    }
+
+  return w.ll;
+}
+
+word_type
+__cmpdi2 (DWtype a, DWtype b)
+{
+  const DWunion au = {.ll = a};
+  const DWunion bu = {.ll = b};
+
+  if (au.s.high < bu.s.high)
+    return 0;
+  else if (au.s.high > bu.s.high)
+    return 2;
+  if ((UWtype) au.s.low < (UWtype) bu.s.low)
+    return 0;
+  else if ((UWtype) au.s.low > (UWtype) bu.s.low)
+    return 2;
+  return 1;
+}
+
+UDWtype
+__udivmoddi4 (UDWtype n, UDWtype d, UDWtype *rp)
+{
+  const DWunion nn = {.ll = n};
+  const DWunion dd = {.ll = d};
+  DWunion rr;
+  UWtype d0, d1, n0, n1, n2;
+  UWtype q0, q1;
+  UWtype b, bm;
+
+  d0 = dd.s.low;
+  d1 = dd.s.high;
+  n0 = nn.s.low;
+  n1 = nn.s.high;
+
+#if !UDIV_NEEDS_NORMALIZATION
+  if (d1 == 0)
+    {
+      if (d0 > n1)
+	{
+	  /* 0q = nn / 0D */
+
+	  udiv_qrnnd (q0, n0, n1, n0, d0);
+	  q1 = 0;
+
+	  /* Remainder in n0.  */
+	}
+      else
+	{
+	  /* qq = NN / 0d */
+
+	  if (d0 == 0)
+	    d0 = 1 / d0;	/* Divide intentionally by zero.  */
+
+	  udiv_qrnnd (q1, n1, 0, n1, d0);
+	  udiv_qrnnd (q0, n0, n1, n0, d0);
+
+	  /* Remainder in n0.  */
+	}
+
+      if (rp != 0)
+	{
+	  rr.s.low = n0;
+	  rr.s.high = 0;
+	  *rp = rr.ll;
+	}
+    }
+
+#else /* UDIV_NEEDS_NORMALIZATION */
+
+  if (d1 == 0)
+    {
+      if (d0 > n1)
+	{
+	  /* 0q = nn / 0D */
+
+	  count_leading_zeros (bm, d0);
+
+	  if (bm != 0)
+	    {
+	      /* Normalize, i.e. make the most significant bit of the
+		 denominator set.  */
+
+	      d0 = d0 << bm;
+	      n1 = (n1 << bm) | (n0 >> (W_TYPE_SIZE - bm));
+	      n0 = n0 << bm;
+	    }
+
+	  udiv_qrnnd (q0, n0, n1, n0, d0);
+	  q1 = 0;
+
+	  /* Remainder in n0 >> bm.  */
+	}
+      else
+	{
+	  /* qq = NN / 0d */
+
+	  if (d0 == 0)
+	    d0 = 1 / d0;	/* Divide intentionally by zero.  */
+
+	  count_leading_zeros (bm, d0);
+
+	  if (bm == 0)
+	    {
+	      /* From (n1 >= d0) /\ (the most significant bit of d0 is set),
+		 conclude (the most significant bit of n1 is set) /\ (the
+		 leading quotient digit q1 = 1).
+
+		 This special case is necessary, not an optimization.
+		 (Shifts counts of W_TYPE_SIZE are undefined.)  */
+
+	      n1 -= d0;
+	      q1 = 1;
+	    }
+	  else
+	    {
+	      /* Normalize.  */
+
+	      b = W_TYPE_SIZE - bm;
+
+	      d0 = d0 << bm;
+	      n2 = n1 >> b;
+	      n1 = (n1 << bm) | (n0 >> b);
+	      n0 = n0 << bm;
+
+	      udiv_qrnnd (q1, n1, n2, n1, d0);
+	    }
+
+	  /* n1 != d0...  */
+
+	  udiv_qrnnd (q0, n0, n1, n0, d0);
+
+	  /* Remainder in n0 >> bm.  */
+	}
+
+      if (rp != 0)
+	{
+	  rr.s.low = n0 >> bm;
+	  rr.s.high = 0;
+	  *rp = rr.ll;
+	}
+    }
+#endif /* UDIV_NEEDS_NORMALIZATION */
+
+  else
+    {
+      if (d1 > n1)
+	{
+	  /* 00 = nn / DD */
+
+	  q0 = 0;
+	  q1 = 0;
+
+	  /* Remainder in n1n0.  */
+	  if (rp != 0)
+	    {
+	      rr.s.low = n0;
+	      rr.s.high = n1;
+	      *rp = rr.ll;
+	    }
+	}
+      else
+	{
+	  /* 0q = NN / dd */
+
+	  count_leading_zeros (bm, d1);
+	  if (bm == 0)
+	    {
+	      /* From (n1 >= d1) /\ (the most significant bit of d1 is set),
+		 conclude (the most significant bit of n1 is set) /\ (the
+		 quotient digit q0 = 0 or 1).
+
+		 This special case is necessary, not an optimization.  */
+
+	      /* The condition on the next line takes advantage of that
+		 n1 >= d1 (true due to program flow).  */
+	      if (n1 > d1 || n0 >= d0)
+		{
+		  q0 = 1;
+		  sub_ddmmss (n1, n0, n1, n0, d1, d0);
+		}
+	      else
+		q0 = 0;
+
+	      q1 = 0;
+
+	      if (rp != 0)
+		{
+		  rr.s.low = n0;
+		  rr.s.high = n1;
+		  *rp = rr.ll;
+		}
+	    }
+	  else
+	    {
+	      UWtype m1, m0;
+	      /* Normalize.  */
+
+	      b = W_TYPE_SIZE - bm;
+
+	      d1 = (d1 << bm) | (d0 >> b);
+	      d0 = d0 << bm;
+	      n2 = n1 >> b;
+	      n1 = (n1 << bm) | (n0 >> b);
+	      n0 = n0 << bm;
+
+	      udiv_qrnnd (q0, n1, n2, n1, d1);
+	      umul_ppmm (m1, m0, q0, d0);
+
+	      if (m1 > n1 || (m1 == n1 && m0 > n0))
+		{
+		  q0--;
+		  sub_ddmmss (m1, m0, m1, m0, d1, d0);
+		}
+
+	      q1 = 0;
+
+	      /* Remainder in (n1n0 - m1m0) >> bm.  */
+	      if (rp != 0)
+		{
+		  sub_ddmmss (n1, n0, n1, n0, m1, m0);
+		  rr.s.low = (n1 << b) | (n0 >> bm);
+		  rr.s.high = n1 >> bm;
+		  *rp = rr.ll;
+		}
+	    }
+	}
+    }
+
+  const DWunion ww = {{.low = q0, .high = q1}};
+  return ww.ll;
+}
+
+DWtype
+__divdi3 (DWtype u, DWtype v)
+{
+  word_type c = 0;
+  DWunion uu = {.ll = u};
+  DWunion vv = {.ll = v};
+  DWtype w;
+
+  if (uu.s.high < 0)
+    c = ~c,
+    uu.ll = -uu.ll;
+  if (vv.s.high < 0)
+    c = ~c,
+    vv.ll = -vv.ll;
+
+  w = __udivmoddi4 (uu.ll, vv.ll, (UDWtype *) 0);
+  if (c)
+    w = -w;
+
+  return w;
+}
+
+DWtype
+__negdi2 (DWtype u)
+{
+  const DWunion uu = {.ll = u};
+  const DWunion w = { {.low = -uu.s.low,
+		       .high = -uu.s.high - ((UWtype) -uu.s.low > 0) } };
+
+  return w.ll;
+}
+
+
+DWtype
+__muldi3 (DWtype u, DWtype v)
+{
+  const DWunion uu = {.ll = u};
+  const DWunion vv = {.ll = v};
+  DWunion  w = {.ll = __umulsidi3 (uu.s.low, vv.s.low)};
+
+  w.s.high += ((UWtype) uu.s.low * (UWtype) vv.s.high
+  + (UWtype) uu.s.high * (UWtype) vv.s.low);
+
+  return w.ll;
+}
+
+DWtype
+__moddi3 (DWtype u, DWtype v)
+{
+  word_type c = 0;
+  DWunion uu = {.ll = u};
+  DWunion vv = {.ll = v};
+  DWtype w;
+
+  if (uu.s.high < 0)
+    c = ~c,
+    uu.ll = -uu.ll;
+  if (vv.s.high < 0)
+    vv.ll = -vv.ll;
+
+  (void) __udivmoddi4 (uu.ll, vv.ll, (UDWtype*)&w);
+  if (c)
+    w = -w;
+
+  return w;
+}
+
+word_type
+__ucmpdi2 (DWtype a, DWtype b)
+{
+  const DWunion au = {.ll = a};
+  const DWunion bu = {.ll = b};
+
+  if ((UWtype) au.s.high < (UWtype) bu.s.high)
+    return 0;
+  else if ((UWtype) au.s.high > (UWtype) bu.s.high)
+    return 2;
+  if ((UWtype) au.s.low < (UWtype) bu.s.low)
+    return 0;
+  else if ((UWtype) au.s.low > (UWtype) bu.s.low)
+    return 2;
+  return 1;
+}
+
+
+UDWtype
+__udivdi3 (UDWtype n, UDWtype d)
+{
+  return __udivmoddi4 (n, d, (UDWtype *) 0);
+}
+
+UDWtype
+__umoddi3 (UDWtype u, UDWtype v)
+{
+  UDWtype w;
+  (void) __udivmoddi4 (u, v, &w);
+
+  return w;
+}
+
+static USItype
+udivmodsi4(USItype num, USItype den, word_type modwanted)
+{
+  USItype bit = 1;
+  USItype res = 0;
+
+  while (den < num && bit && !(den & (1L<<31)))
+    {
+      den <<=1;
+      bit <<=1;
+    }
+  while (bit)
+    {
+      if (num >= den)
+	{
+	  num -= den;
+	  res |= bit;
+	}
+      bit >>=1;
+      den >>=1;
+    }
+  if (modwanted) return num;
+  return res;
+}
+
+SItype
+__divsi3 (SItype a, SItype b)
+{
+  word_type neg = 0;
+  SItype res;
+
+  if (a < 0)
+    {
+      a = -a;
+      neg = !neg;
+    }
+
+  if (b < 0)
+    {
+      b = -b;
+      neg = !neg;
+    }
+
+  res = udivmodsi4 (a, b, 0);
+
+  if (neg)
+    res = -res;
+
+  return res;
+}
+
+
+SItype
+__udivsi3 (SItype a, SItype b)
+{
+  return udivmodsi4 (a, b, 0);
+}
+
+
+SItype
+__modsi3 (SItype a, SItype b)
+{
+  word_type neg = 0;
+  SItype res;
+
+  if (a < 0)
+    {
+      a = -a;
+      neg = 1;
+    }
+
+  if (b < 0)
+    b = -b;
+
+  res = udivmodsi4 (a, b, 1);
+
+  if (neg)
+    res = -res;
+
+  return res;
+}
+
+SItype
+__mulsi3 (SItype a, SItype b)
+{
+  SItype res = 0;
+  USItype cnt = a;
+
+  while (cnt)
+    {
+      if (cnt & 1)
+        {
+	  res += b;
+	}
+      b <<= 1;
+      cnt >>= 1;
+    }
+
+  return res;
+}
+
+SItype
+__umodsi3 (SItype a, SItype b)
+
+{
+  return udivmodsi4 (a, b, 1);
+}
+
+int
+__gcc_bcmp (const unsigned char *s1, const unsigned char *s2, unsigned long size)
+{
+  while (size > 0)
+    {
+      const unsigned char c1 = *s1++, c2 = *s2++;
+      if (c1 != c2)
+	return c1 - c2;
+      size--;
+    }
+  return 0;
+}
diff --git a/arch/nios2/lib/longlong.h b/arch/nios2/lib/longlong.h
new file mode 100644
index 0000000..392f7e7
--- /dev/null
+++ b/arch/nios2/lib/longlong.h
@@ -0,0 +1,263 @@
+/* longlong.h -- definitions for mixed size 32/64 bit arithmetic.
+   Copyright (C) 1991, 1992, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2004,
+   2005  Free Software Foundation, Inc.
+
+   This definition file is free software; you can redistribute it
+   and/or modify it under the terms of the GNU General Public
+   License as published by the Free Software Foundation; either
+   version 2, or (at your option) any later version.
+
+   This definition file is distributed in the hope that it will be
+   useful, but WITHOUT ANY WARRANTY; without even the implied
+   warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+   See the GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this program; if not, write to the Free Software
+   Foundation, Inc., 51 Franklin Street, Fifth Floor,
+   Boston, MA 02110-1301, USA.  */
+
+/* You have to define the following before including this file:
+
+   UWtype -- An unsigned type, default type for operations (typically a "word")
+   UHWtype -- An unsigned type, at least half the size of UWtype.
+   UDWtype -- An unsigned type, at least twice as large a UWtype
+   W_TYPE_SIZE -- size in bits of UWtype
+
+   UQItype -- Unsigned 8 bit type.
+   SItype, USItype -- Signed and unsigned 32 bit types.
+   DItype, UDItype -- Signed and unsigned 64 bit types.
+
+   On a 32 bit machine UWtype should typically be USItype;
+   on a 64 bit machine, UWtype should typically be UDItype.  */
+
+#define __BITS4 (W_TYPE_SIZE / 4)
+#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))
+
+#ifndef W_TYPE_SIZE
+#define W_TYPE_SIZE	32
+#define UWtype		USItype
+#define UHWtype		USItype
+#define UDWtype		UDItype
+#endif
+
+extern const UQItype __clz_tab[256];
+
+/* Define auxiliary asm macros.
+
+   1) umul_ppmm(high_prod, low_prod, multiplier, multiplicand) multiplies two
+   UWtype integers MULTIPLIER and MULTIPLICAND, and generates a two UWtype
+   word product in HIGH_PROD and LOW_PROD.
+
+   2) __umulsidi3(a,b) multiplies two UWtype integers A and B, and returns a
+   UDWtype product.  This is just a variant of umul_ppmm.
+
+   3) udiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
+   denominator) divides a UDWtype, composed by the UWtype integers
+   HIGH_NUMERATOR and LOW_NUMERATOR, by DENOMINATOR and places the quotient
+   in QUOTIENT and the remainder in REMAINDER.  HIGH_NUMERATOR must be less
+   than DENOMINATOR for correct operation.  If, in addition, the most
+   significant bit of DENOMINATOR must be 1, then the pre-processor symbol
+   UDIV_NEEDS_NORMALIZATION is defined to 1.
+
+   4) sdiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
+   denominator).  Like udiv_qrnnd but the numbers are signed.  The quotient
+   is rounded towards 0.
+
+   5) count_leading_zeros(count, x) counts the number of zero-bits from the
+   msb to the first nonzero bit in the UWtype X.  This is the number of
+   steps X needs to be shifted left to set the msb.  Undefined for X == 0,
+   unless the symbol COUNT_LEADING_ZEROS_0 is defined to some value.
+
+   6) count_trailing_zeros(count, x) like count_leading_zeros, but counts
+   from the least significant end.
+
+   7) add_ssaaaa(high_sum, low_sum, high_addend_1, low_addend_1,
+   high_addend_2, low_addend_2) adds two UWtype integers, composed by
+   HIGH_ADDEND_1 and LOW_ADDEND_1, and HIGH_ADDEND_2 and LOW_ADDEND_2
+   respectively.  The result is placed in HIGH_SUM and LOW_SUM.  Overflow
+   (i.e. carry out) is not stored anywhere, and is lost.
+
+   8) sub_ddmmss(high_difference, low_difference, high_minuend, low_minuend,
+   high_subtrahend, low_subtrahend) subtracts two two-word UWtype integers,
+   composed by HIGH_MINUEND_1 and LOW_MINUEND_1, and HIGH_SUBTRAHEND_2 and
+   LOW_SUBTRAHEND_2 respectively.  The result is placed in HIGH_DIFFERENCE
+   and LOW_DIFFERENCE.  Overflow (i.e. carry out) is not stored anywhere,
+   and is lost.
+
+   If any of these macros are left undefined for a particular CPU,
+   C macros are used.  */
+
+/* The CPUs come in alphabetical order below.
+
+   Please add support for more CPUs here, or improve the current support
+   for the CPUs below!
+   (E.g. WE32100, IBM360.)  */
+
+/* Snipped per CPU support */
+
+/* If this machine has no inline assembler, use C macros.  */
+
+#if !defined (add_ssaaaa)
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  do {									\
+    UWtype __x;								\
+    __x = (al) + (bl);							\
+    (sh) = (ah) + (bh) + (__x < (al));					\
+    (sl) = __x;								\
+  } while (0)
+#endif
+
+#if !defined (sub_ddmmss)
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  do {									\
+    UWtype __x;								\
+    __x = (al) - (bl);							\
+    (sh) = (ah) - (bh) - (__x > (al));					\
+    (sl) = __x;								\
+  } while (0)
+#endif
+
+/* If we lack umul_ppmm but have smul_ppmm, define umul_ppmm in terms of
+   smul_ppmm.  */
+#if !defined (umul_ppmm) && defined (smul_ppmm)
+#define umul_ppmm(w1, w0, u, v)						\
+  do {									\
+    UWtype __w1;							\
+    UWtype __xm0 = (u), __xm1 = (v);					\
+    smul_ppmm (__w1, w0, __xm0, __xm1);					\
+    (w1) = __w1 + (-(__xm0 >> (W_TYPE_SIZE - 1)) & __xm1)		\
+		+ (-(__xm1 >> (W_TYPE_SIZE - 1)) & __xm0);		\
+  } while (0)
+#endif
+
+/* If we still don't have umul_ppmm, define it using plain C.  */
+#if !defined (umul_ppmm)
+#define umul_ppmm(w1, w0, u, v)						\
+  do {									\
+    UWtype __x0, __x1, __x2, __x3;					\
+    UHWtype __ul, __vl, __uh, __vh;					\
+									\
+    __ul = __ll_lowpart (u);						\
+    __uh = __ll_highpart (u);						\
+    __vl = __ll_lowpart (v);						\
+    __vh = __ll_highpart (v);						\
+									\
+    __x0 = (UWtype) __ul * __vl;					\
+    __x1 = (UWtype) __ul * __vh;					\
+    __x2 = (UWtype) __uh * __vl;					\
+    __x3 = (UWtype) __uh * __vh;					\
+									\
+    __x1 += __ll_highpart (__x0);/* this can't give carry */		\
+    __x1 += __x2;		/* but this indeed can */		\
+    if (__x1 < __x2)		/* did we get it? */			\
+      __x3 += __ll_B;		/* yes, add it in the proper pos.  */	\
+									\
+    (w1) = __x3 + __ll_highpart (__x1);					\
+    (w0) = __ll_lowpart (__x1) * __ll_B + __ll_lowpart (__x0);		\
+  } while (0)
+#endif
+
+#if !defined (__umulsidi3)
+#define __umulsidi3(u, v) \
+  ({DWunion __w;							\
+    umul_ppmm (__w.s.high, __w.s.low, u, v);				\
+    __w.ll; })
+#endif
+
+/* Define this unconditionally, so it can be used for debugging.  */
+#define __udiv_qrnnd_c(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)
+
+/* If the processor has no udiv_qrnnd but sdiv_qrnnd, go through
+   __udiv_w_sdiv (defined in libgcc or elsewhere).  */
+#if !defined (udiv_qrnnd) && defined (sdiv_qrnnd)
+#define udiv_qrnnd(q, r, nh, nl, d) \
+  do {									\
+    USItype __r;							\
+    (q) = __udiv_w_sdiv (&__r, nh, nl, d);				\
+    (r) = __r;								\
+  } while (0)
+#endif
+
+/* If udiv_qrnnd was not defined for this processor, use __udiv_qrnnd_c.  */
+#if !defined (udiv_qrnnd)
+#define UDIV_NEEDS_NORMALIZATION 1
+#define udiv_qrnnd __udiv_qrnnd_c
+#endif
+
+#if !defined (count_leading_zeros)
+#define count_leading_zeros(count, x) \
+  do {									\
+    UWtype __xr = (x);							\
+    UWtype __a;								\
+									\
+    if (W_TYPE_SIZE <= 32)						\
+      {									\
+	__a = __xr < ((UWtype)1<<2*__BITS4)				\
+	  ? (__xr < ((UWtype)1<<__BITS4) ? 0 : __BITS4)			\
+	  : (__xr < ((UWtype)1<<3*__BITS4) ?  2*__BITS4 : 3*__BITS4);	\
+      }									\
+    else								\
+      {									\
+	for (__a = W_TYPE_SIZE - 8; __a > 0; __a -= 8)			\
+	  if (((__xr >> __a) & 0xff) != 0)				\
+	    break;							\
+      }									\
+									\
+    (count) = W_TYPE_SIZE - (__clz_tab[__xr >> __a] + __a);		\
+  } while (0)
+#define COUNT_LEADING_ZEROS_0 W_TYPE_SIZE
+#endif
+
+#if !defined (count_trailing_zeros)
+/* Define count_trailing_zeros using count_leading_zeros.  The latter might be
+   defined in asm, but if it is not, the C version above is good enough.  */
+#define count_trailing_zeros(count, x) \
+  do {									\
+    UWtype __ctz_x = (x);						\
+    UWtype __ctz_c;							\
+    count_leading_zeros (__ctz_c, __ctz_x & -__ctz_x);			\
+    (count) = W_TYPE_SIZE - 1 - __ctz_c;				\
+  } while (0)
+#endif
+
+#ifndef UDIV_NEEDS_NORMALIZATION
+#define UDIV_NEEDS_NORMALIZATION 0
+#endif
diff --git a/arch/nios2/lib/math.h b/arch/nios2/lib/math.h
deleted file mode 100644
index f0aed8e..0000000
--- a/arch/nios2/lib/math.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#define BITS_PER_UNIT	8
-
-typedef	 int HItype			__attribute__ ((mode (HI)));
-typedef unsigned int UHItype		__attribute__ ((mode (HI)));
-
-typedef		 int SItype		__attribute__ ((mode (SI)));
-typedef unsigned int USItype		__attribute__ ((mode (SI)));
-
-typedef int word_type			__attribute__ ((mode (__word__)));
-
-struct SIstruct {HItype low, high;};
-
-typedef union {
-	struct SIstruct s;
-	SItype ll;
-} SIunion;
diff --git a/arch/nios2/lib/mult.c b/arch/nios2/lib/mult.c
deleted file mode 100644
index ec8139e..0000000
--- a/arch/nios2/lib/mult.c
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- * This file is part of GNU CC.
- *
- * GNU CC is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published
- * by the Free Software Foundation; either version 2, or (at your
- * option) any later version.
- *
- * GNU CC is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public
- * License along with GNU CC; see the file COPYING.  If not, write
- * to the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
- */
-
-
-#include <common.h>
-
-#if !defined(CONFIG_SYS_NIOS_MULT_HW) && !defined(CONFIG_SYS_NIOS_MULT_MSTEP)
-
-#include "math.h"
-
-USItype __mulsi3 (USItype a, USItype b)
-{
-	USItype c = 0;
-
-	while (a != 0) {
-		if (a & 1)
-			c += b;
-		a >>= 1;
-		b <<= 1;
-	}
-
-	return c;
-}
-
-
-UHItype __mulhi3 (UHItype a, UHItype b)
-{
-	UHItype c = 0;
-
-	while (a != 0) {
-		if (a & 1)
-			c += b;
-		a >>= 1;
-		b <<= 1;
-	}
-
-	return c;
-}
-
-#endif /*!defined(CONFIG_SYS_NIOS_MULT_HW) && !defined(CONFIG_SYS_NIOS_MULT_MSTEP) */
-- 
1.5.5.6

[U-Boot] [PATCH] nios2: fix div64 issue for gcc4

[Scott McNutt]

Applied to:
    git://git.denx.de/u-boot-nios.git next

Thanks,
--Scott



Thomas Chou wrote:
> This patch fixes the run-time error on div64 when built with
> gcc4, which was reported by jhwu0625 on nios forum. It merges
> math support from libgcc of gcc4. This patch is copied from
> nios2-linux.
> 
> It works with both gcc3 and gcc4. The old mult.c, divmod.c and
> math.h are removed.
> 
> Signed-off-by: Thomas Chou <thomas@wytron.com.tw>
> ---
>  arch/nios2/lib/Makefile   |    3 +-
>  arch/nios2/lib/divmod.c   |  101 --------
>  arch/nios2/lib/libgcc.c   |  592 +++++++++++++++++++++++++++++++++++++++++++++
>  arch/nios2/lib/longlong.h |  263 ++++++++++++++++++++
>  arch/nios2/lib/math.h     |   16 --
>  arch/nios2/lib/mult.c     |   56 -----
>  6 files changed, 856 insertions(+), 175 deletions(-)
>  delete mode 100644 arch/nios2/lib/divmod.c
>  create mode 100644 arch/nios2/lib/libgcc.c
>  create mode 100644 arch/nios2/lib/longlong.h
>  delete mode 100644 arch/nios2/lib/math.h
>  delete mode 100644 arch/nios2/lib/mult.c
> 
> diff --git a/arch/nios2/lib/Makefile b/arch/nios2/lib/Makefile
> index b69bc38..92320c5 100644
> --- a/arch/nios2/lib/Makefile
> +++ b/arch/nios2/lib/Makefile
> @@ -29,8 +29,7 @@ SOBJS-y	+= cache.o
>  
>  COBJS-y	+= board.o
>  COBJS-y	+= bootm.o
> -COBJS-y	+= divmod.o
> -COBJS-y	+= mult.o
> +COBJS-y	+= libgcc.o
>  COBJS-y	+= time.o
>  
>  SRCS	:= $(SOBJS-y:.o=.S) $(COBJS-y:.o=.c)
> diff --git a/arch/nios2/lib/divmod.c b/arch/nios2/lib/divmod.c
> deleted file mode 100644
> index 3c7e71e..0000000
> --- a/arch/nios2/lib/divmod.c
> +++ /dev/null
> @@ -1,101 +0,0 @@
> -/*
> - * This file is part of GNU CC.
> - *
> - * GNU CC is free software; you can redistribute it and/or modify
> - * it under the terms of the GNU General Public License as published
> - * by the Free Software Foundation; either version 2, or (at your
> - * option) any later version.
> - *
> - * GNU CC is distributed in the hope that it will be useful,
> - * but WITHOUT ANY WARRANTY; without even the implied warranty of
> - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
> - * GNU General Public License for more details.
> - *
> - * You should have received a copy of the GNU General Public
> - * License along with GNU CC; see the file COPYING.  If not, write
> - * to the Free Software Foundation, 59 Temple Place - Suite 330,
> - * Boston, MA 02111-1307, USA.
> - */
> -
> -
> -#include "math.h"
> -
> -USItype udivmodsi4 (USItype num, USItype den, word_type modwanted)
> -{
> -	USItype bit = 1;
> -	USItype res = 0;
> -
> -	while (den < num && bit && !(den & (1L << 31))) {
> -		den <<= 1;
> -		bit <<= 1;
> -	}
> -	while (bit) {
> -		if (num >= den) {
> -			num -= den;
> -			res |= bit;
> -		}
> -		bit >>= 1;
> -		den >>= 1;
> -	}
> -	if (modwanted)
> -		return num;
> -	return res;
> -}
> -
> -
> -SItype __divsi3 (SItype a, SItype b)
> -{
> -	word_type neg = 0;
> -	SItype res;
> -
> -	if (a < 0) {
> -		a = -a;
> -		neg = !neg;
> -	}
> -
> -	if (b < 0) {
> -		b = -b;
> -		neg = !neg;
> -	}
> -
> -	res = udivmodsi4 (a, b, 0);
> -
> -	if (neg)
> -		res = -res;
> -
> -	return res;
> -}
> -
> -
> -SItype __modsi3 (SItype a, SItype b)
> -{
> -	word_type neg = 0;
> -	SItype res;
> -
> -	if (a < 0) {
> -		a = -a;
> -		neg = 1;
> -	}
> -
> -	if (b < 0)
> -		b = -b;
> -
> -	res = udivmodsi4 (a, b, 1);
> -
> -	if (neg)
> -		res = -res;
> -
> -	return res;
> -}
> -
> -
> -SItype __udivsi3 (SItype a, SItype b)
> -{
> -	return udivmodsi4 (a, b, 0);
> -}
> -
> -
> -SItype __umodsi3 (SItype a, SItype b)
> -{
> -	return udivmodsi4 (a, b, 1);
> -}
> diff --git a/arch/nios2/lib/libgcc.c b/arch/nios2/lib/libgcc.c
> new file mode 100644
> index 0000000..dc05627
> --- /dev/null
> +++ b/arch/nios2/lib/libgcc.c
> @@ -0,0 +1,592 @@
> +/*
> + * This file is part of GNU CC.
> + *
> + * GNU CC is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License as published
> + * by the Free Software Foundation; either version 2, or (at your
> + * option) any later version.
> + *
> + * GNU CC is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
> + * GNU General Public License for more details.
> + *
> + * You should have received a copy of the GNU General Public
> + * License along with GNU CC; see the file COPYING.  If not, write
> + * to the Free Software Foundation, 59 Temple Place - Suite 330,
> + * Boston, MA 02111-1307, USA.
> + */
> +
> +typedef unsigned int UWtype;
> +typedef unsigned int UHWtype;
> +typedef unsigned long long UDWtype;
> +#define W_TYPE_SIZE 32
> +
> +typedef unsigned char UQItype;
> +typedef long SItype;
> +typedef unsigned long USItype;
> +typedef long long DItype;
> +typedef unsigned long long DSItype;
> +
> +#include "longlong.h"
> +
> +
> +typedef int word_type;
> +typedef long Wtype;
> +typedef long long DWtype;
> +
> +struct DWstruct { Wtype low, high;};
> +
> +typedef union
> +{
> +  struct DWstruct s;
> +  DWtype ll;
> +} DWunion;
> +
> +#define BITS_PER_UNIT 8
> +
> +UDWtype
> +__udivmoddi4 (UDWtype n, UDWtype d, UDWtype *rp);
> +
> +const UQItype __clz_tab[256] =
> +{
> +  0,1,2,2,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,
> +  6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,
> +  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
> +  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
> +  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
> +  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
> +  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
> +  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8
> +};
> +
> +
> +DWtype
> +__ashldi3 (DWtype u, word_type b)
> +{
> +  if (b == 0)
> +    return u;
> +
> +  const DWunion uu = {.ll = u};
> +  const word_type bm = (sizeof (Wtype) * BITS_PER_UNIT) - b;
> +  DWunion w;
> +
> +  if (bm <= 0)
> +    {
> +      w.s.low = 0;
> +      w.s.high = (UWtype) uu.s.low << -bm;
> +    }
> +  else
> +    {
> +      const UWtype carries = (UWtype) uu.s.low >> bm;
> +
> +      w.s.low = (UWtype) uu.s.low << b;
> +      w.s.high = ((UWtype) uu.s.high << b) | carries;
> +    }
> +
> +  return w.ll;
> +}
> +
> +DWtype
> +__ashrdi3 (DWtype u, word_type b)
> +{
> +  if (b == 0)
> +    return u;
> +
> +  const DWunion uu = {.ll = u};
> +  const word_type bm = (sizeof (Wtype) * BITS_PER_UNIT) - b;
> +  DWunion w;
> +
> +  if (bm <= 0)
> +    {
> +      /* w.s.high = 1..1 or 0..0 */
> +      w.s.high = uu.s.high >> (sizeof (Wtype) * BITS_PER_UNIT - 1);
> +      w.s.low = uu.s.high >> -bm;
> +    }
> +  else
> +    {
> +      const UWtype carries = (UWtype) uu.s.high << bm;
> +
> +      w.s.high = uu.s.high >> b;
> +      w.s.low = ((UWtype) uu.s.low >> b) | carries;
> +    }
> +
> +  return w.ll;
> +}
> +
> +DWtype
> +__lshrdi3 (DWtype u, word_type b)
> +{
> +  if (b == 0)
> +    return u;
> +
> +  const DWunion uu = {.ll = u};
> +  const word_type bm = (sizeof (Wtype) * BITS_PER_UNIT) - b;
> +  DWunion w;
> +
> +  if (bm <= 0)
> +    {
> +      w.s.high = 0;
> +      w.s.low = (UWtype) uu.s.high >> -bm;
> +    }
> +  else
> +    {
> +      const UWtype carries = (UWtype) uu.s.high << bm;
> +
> +      w.s.high = (UWtype) uu.s.high >> b;
> +      w.s.low = ((UWtype) uu.s.low >> b) | carries;
> +    }
> +
> +  return w.ll;
> +}
> +
> +word_type
> +__cmpdi2 (DWtype a, DWtype b)
> +{
> +  const DWunion au = {.ll = a};
> +  const DWunion bu = {.ll = b};
> +
> +  if (au.s.high < bu.s.high)
> +    return 0;
> +  else if (au.s.high > bu.s.high)
> +    return 2;
> +  if ((UWtype) au.s.low < (UWtype) bu.s.low)
> +    return 0;
> +  else if ((UWtype) au.s.low > (UWtype) bu.s.low)
> +    return 2;
> +  return 1;
> +}
> +
> +UDWtype
> +__udivmoddi4 (UDWtype n, UDWtype d, UDWtype *rp)
> +{
> +  const DWunion nn = {.ll = n};
> +  const DWunion dd = {.ll = d};
> +  DWunion rr;
> +  UWtype d0, d1, n0, n1, n2;
> +  UWtype q0, q1;
> +  UWtype b, bm;
> +
> +  d0 = dd.s.low;
> +  d1 = dd.s.high;
> +  n0 = nn.s.low;
> +  n1 = nn.s.high;
> +
> +#if !UDIV_NEEDS_NORMALIZATION
> +  if (d1 == 0)
> +    {
> +      if (d0 > n1)
> +	{
> +	  /* 0q = nn / 0D */
> +
> +	  udiv_qrnnd (q0, n0, n1, n0, d0);
> +	  q1 = 0;
> +
> +	  /* Remainder in n0.  */
> +	}
> +      else
> +	{
> +	  /* qq = NN / 0d */
> +
> +	  if (d0 == 0)
> +	    d0 = 1 / d0;	/* Divide intentionally by zero.  */
> +
> +	  udiv_qrnnd (q1, n1, 0, n1, d0);
> +	  udiv_qrnnd (q0, n0, n1, n0, d0);
> +
> +	  /* Remainder in n0.  */
> +	}
> +
> +      if (rp != 0)
> +	{
> +	  rr.s.low = n0;
> +	  rr.s.high = 0;
> +	  *rp = rr.ll;
> +	}
> +    }
> +
> +#else /* UDIV_NEEDS_NORMALIZATION */
> +
> +  if (d1 == 0)
> +    {
> +      if (d0 > n1)
> +	{
> +	  /* 0q = nn / 0D */
> +
> +	  count_leading_zeros (bm, d0);
> +
> +	  if (bm != 0)
> +	    {
> +	      /* Normalize, i.e. make the most significant bit of the
> +		 denominator set.  */
> +
> +	      d0 = d0 << bm;
> +	      n1 = (n1 << bm) | (n0 >> (W_TYPE_SIZE - bm));
> +	      n0 = n0 << bm;
> +	    }
> +
> +	  udiv_qrnnd (q0, n0, n1, n0, d0);
> +	  q1 = 0;
> +
> +	  /* Remainder in n0 >> bm.  */
> +	}
> +      else
> +	{
> +	  /* qq = NN / 0d */
> +
> +	  if (d0 == 0)
> +	    d0 = 1 / d0;	/* Divide intentionally by zero.  */
> +
> +	  count_leading_zeros (bm, d0);
> +
> +	  if (bm == 0)
> +	    {
> +	      /* From (n1 >= d0) /\ (the most significant bit of d0 is set),
> +		 conclude (the most significant bit of n1 is set) /\ (the
> +		 leading quotient digit q1 = 1).
> +
> +		 This special case is necessary, not an optimization.
> +		 (Shifts counts of W_TYPE_SIZE are undefined.)  */
> +
> +	      n1 -= d0;
> +	      q1 = 1;
> +	    }
> +	  else
> +	    {
> +	      /* Normalize.  */
> +
> +	      b = W_TYPE_SIZE - bm;
> +
> +	      d0 = d0 << bm;
> +	      n2 = n1 >> b;
> +	      n1 = (n1 << bm) | (n0 >> b);
> +	      n0 = n0 << bm;
> +
> +	      udiv_qrnnd (q1, n1, n2, n1, d0);
> +	    }
> +
> +	  /* n1 != d0...  */
> +
> +	  udiv_qrnnd (q0, n0, n1, n0, d0);
> +
> +	  /* Remainder in n0 >> bm.  */
> +	}
> +
> +      if (rp != 0)
> +	{
> +	  rr.s.low = n0 >> bm;
> +	  rr.s.high = 0;
> +	  *rp = rr.ll;
> +	}
> +    }
> +#endif /* UDIV_NEEDS_NORMALIZATION */
> +
> +  else
> +    {
> +      if (d1 > n1)
> +	{
> +	  /* 00 = nn / DD */
> +
> +	  q0 = 0;
> +	  q1 = 0;
> +
> +	  /* Remainder in n1n0.  */
> +	  if (rp != 0)
> +	    {
> +	      rr.s.low = n0;
> +	      rr.s.high = n1;
> +	      *rp = rr.ll;
> +	    }
> +	}
> +      else
> +	{
> +	  /* 0q = NN / dd */
> +
> +	  count_leading_zeros (bm, d1);
> +	  if (bm == 0)
> +	    {
> +	      /* From (n1 >= d1) /\ (the most significant bit of d1 is set),
> +		 conclude (the most significant bit of n1 is set) /\ (the
> +		 quotient digit q0 = 0 or 1).
> +
> +		 This special case is necessary, not an optimization.  */
> +
> +	      /* The condition on the next line takes advantage of that
> +		 n1 >= d1 (true due to program flow).  */
> +	      if (n1 > d1 || n0 >= d0)
> +		{
> +		  q0 = 1;
> +		  sub_ddmmss (n1, n0, n1, n0, d1, d0);
> +		}
> +	      else
> +		q0 = 0;
> +
> +	      q1 = 0;
> +
> +	      if (rp != 0)
> +		{
> +		  rr.s.low = n0;
> +		  rr.s.high = n1;
> +		  *rp = rr.ll;
> +		}
> +	    }
> +	  else
> +	    {
> +	      UWtype m1, m0;
> +	      /* Normalize.  */
> +
> +	      b = W_TYPE_SIZE - bm;
> +
> +	      d1 = (d1 << bm) | (d0 >> b);
> +	      d0 = d0 << bm;
> +	      n2 = n1 >> b;
> +	      n1 = (n1 << bm) | (n0 >> b);
> +	      n0 = n0 << bm;
> +
> +	      udiv_qrnnd (q0, n1, n2, n1, d1);
> +	      umul_ppmm (m1, m0, q0, d0);
> +
> +	      if (m1 > n1 || (m1 == n1 && m0 > n0))
> +		{
> +		  q0--;
> +		  sub_ddmmss (m1, m0, m1, m0, d1, d0);
> +		}
> +
> +	      q1 = 0;
> +
> +	      /* Remainder in (n1n0 - m1m0) >> bm.  */
> +	      if (rp != 0)
> +		{
> +		  sub_ddmmss (n1, n0, n1, n0, m1, m0);
> +		  rr.s.low = (n1 << b) | (n0 >> bm);
> +		  rr.s.high = n1 >> bm;
> +		  *rp = rr.ll;
> +		}
> +	    }
> +	}
> +    }
> +
> +  const DWunion ww = {{.low = q0, .high = q1}};
> +  return ww.ll;
> +}
> +
> +DWtype
> +__divdi3 (DWtype u, DWtype v)
> +{
> +  word_type c = 0;
> +  DWunion uu = {.ll = u};
> +  DWunion vv = {.ll = v};
> +  DWtype w;
> +
> +  if (uu.s.high < 0)
> +    c = ~c,
> +    uu.ll = -uu.ll;
> +  if (vv.s.high < 0)
> +    c = ~c,
> +    vv.ll = -vv.ll;
> +
> +  w = __udivmoddi4 (uu.ll, vv.ll, (UDWtype *) 0);
> +  if (c)
> +    w = -w;
> +
> +  return w;
> +}
> +
> +DWtype
> +__negdi2 (DWtype u)
> +{
> +  const DWunion uu = {.ll = u};
> +  const DWunion w = { {.low = -uu.s.low,
> +		       .high = -uu.s.high - ((UWtype) -uu.s.low > 0) } };
> +
> +  return w.ll;
> +}
> +
> +
> +DWtype
> +__muldi3 (DWtype u, DWtype v)
> +{
> +  const DWunion uu = {.ll = u};
> +  const DWunion vv = {.ll = v};
> +  DWunion  w = {.ll = __umulsidi3 (uu.s.low, vv.s.low)};
> +
> +  w.s.high += ((UWtype) uu.s.low * (UWtype) vv.s.high
> +  + (UWtype) uu.s.high * (UWtype) vv.s.low);
> +
> +  return w.ll;
> +}
> +
> +DWtype
> +__moddi3 (DWtype u, DWtype v)
> +{
> +  word_type c = 0;
> +  DWunion uu = {.ll = u};
> +  DWunion vv = {.ll = v};
> +  DWtype w;
> +
> +  if (uu.s.high < 0)
> +    c = ~c,
> +    uu.ll = -uu.ll;
> +  if (vv.s.high < 0)
> +    vv.ll = -vv.ll;
> +
> +  (void) __udivmoddi4 (uu.ll, vv.ll, (UDWtype*)&w);
> +  if (c)
> +    w = -w;
> +
> +  return w;
> +}
> +
> +word_type
> +__ucmpdi2 (DWtype a, DWtype b)
> +{
> +  const DWunion au = {.ll = a};
> +  const DWunion bu = {.ll = b};
> +
> +  if ((UWtype) au.s.high < (UWtype) bu.s.high)
> +    return 0;
> +  else if ((UWtype) au.s.high > (UWtype) bu.s.high)
> +    return 2;
> +  if ((UWtype) au.s.low < (UWtype) bu.s.low)
> +    return 0;
> +  else if ((UWtype) au.s.low > (UWtype) bu.s.low)
> +    return 2;
> +  return 1;
> +}
> +
> +
> +UDWtype
> +__udivdi3 (UDWtype n, UDWtype d)
> +{
> +  return __udivmoddi4 (n, d, (UDWtype *) 0);
> +}
> +
> +UDWtype
> +__umoddi3 (UDWtype u, UDWtype v)
> +{
> +  UDWtype w;
> +  (void) __udivmoddi4 (u, v, &w);
> +
> +  return w;
> +}
> +
> +static USItype
> +udivmodsi4(USItype num, USItype den, word_type modwanted)
> +{
> +  USItype bit = 1;
> +  USItype res = 0;
> +
> +  while (den < num && bit && !(den & (1L<<31)))
> +    {
> +      den <<=1;
> +      bit <<=1;
> +    }
> +  while (bit)
> +    {
> +      if (num >= den)
> +	{
> +	  num -= den;
> +	  res |= bit;
> +	}
> +      bit >>=1;
> +      den >>=1;
> +    }
> +  if (modwanted) return num;
> +  return res;
> +}
> +
> +SItype
> +__divsi3 (SItype a, SItype b)
> +{
> +  word_type neg = 0;
> +  SItype res;
> +
> +  if (a < 0)
> +    {
> +      a = -a;
> +      neg = !neg;
> +    }
> +
> +  if (b < 0)
> +    {
> +      b = -b;
> +      neg = !neg;
> +    }
> +
> +  res = udivmodsi4 (a, b, 0);
> +
> +  if (neg)
> +    res = -res;
> +
> +  return res;
> +}
> +
> +
> +SItype
> +__udivsi3 (SItype a, SItype b)
> +{
> +  return udivmodsi4 (a, b, 0);
> +}
> +
> +
> +SItype
> +__modsi3 (SItype a, SItype b)
> +{
> +  word_type neg = 0;
> +  SItype res;
> +
> +  if (a < 0)
> +    {
> +      a = -a;
> +      neg = 1;
> +    }
> +
> +  if (b < 0)
> +    b = -b;
> +
> +  res = udivmodsi4 (a, b, 1);
> +
> +  if (neg)
> +    res = -res;
> +
> +  return res;
> +}
> +
> +SItype
> +__mulsi3 (SItype a, SItype b)
> +{
> +  SItype res = 0;
> +  USItype cnt = a;
> +
> +  while (cnt)
> +    {
> +      if (cnt & 1)
> +        {
> +	  res += b;
> +	}
> +      b <<= 1;
> +      cnt >>= 1;
> +    }
> +
> +  return res;
> +}
> +
> +SItype
> +__umodsi3 (SItype a, SItype b)
> +
> +{
> +  return udivmodsi4 (a, b, 1);
> +}
> +
> +int
> +__gcc_bcmp (const unsigned char *s1, const unsigned char *s2, unsigned long size)
> +{
> +  while (size > 0)
> +    {
> +      const unsigned char c1 = *s1++, c2 = *s2++;
> +      if (c1 != c2)
> +	return c1 - c2;
> +      size--;
> +    }
> +  return 0;
> +}
> diff --git a/arch/nios2/lib/longlong.h b/arch/nios2/lib/longlong.h
> new file mode 100644
> index 0000000..392f7e7
> --- /dev/null
> +++ b/arch/nios2/lib/longlong.h
> @@ -0,0 +1,263 @@
> +/* longlong.h -- definitions for mixed size 32/64 bit arithmetic.
> +   Copyright (C) 1991, 1992, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2004,
> +   2005  Free Software Foundation, Inc.
> +
> +   This definition file is free software; you can redistribute it
> +   and/or modify it under the terms of the GNU General Public
> +   License as published by the Free Software Foundation; either
> +   version 2, or (at your option) any later version.
> +
> +   This definition file is distributed in the hope that it will be
> +   useful, but WITHOUT ANY WARRANTY; without even the implied
> +   warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
> +   See the GNU General Public License for more details.
> +
> +   You should have received a copy of the GNU General Public License
> +   along with this program; if not, write to the Free Software
> +   Foundation, Inc., 51 Franklin Street, Fifth Floor,
> +   Boston, MA 02110-1301, USA.  */
> +
> +/* You have to define the following before including this file:
> +
> +   UWtype -- An unsigned type, default type for operations (typically a "word")
> +   UHWtype -- An unsigned type, at least half the size of UWtype.
> +   UDWtype -- An unsigned type, at least twice as large a UWtype
> +   W_TYPE_SIZE -- size in bits of UWtype
> +
> +   UQItype -- Unsigned 8 bit type.
> +   SItype, USItype -- Signed and unsigned 32 bit types.
> +   DItype, UDItype -- Signed and unsigned 64 bit types.
> +
> +   On a 32 bit machine UWtype should typically be USItype;
> +   on a 64 bit machine, UWtype should typically be UDItype.  */
> +
> +#define __BITS4 (W_TYPE_SIZE / 4)
> +#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))
> +
> +#ifndef W_TYPE_SIZE
> +#define W_TYPE_SIZE	32
> +#define UWtype		USItype
> +#define UHWtype		USItype
> +#define UDWtype		UDItype
> +#endif
> +
> +extern const UQItype __clz_tab[256];
> +
> +/* Define auxiliary asm macros.
> +
> +   1) umul_ppmm(high_prod, low_prod, multiplier, multiplicand) multiplies two
> +   UWtype integers MULTIPLIER and MULTIPLICAND, and generates a two UWtype
> +   word product in HIGH_PROD and LOW_PROD.
> +
> +   2) __umulsidi3(a,b) multiplies two UWtype integers A and B, and returns a
> +   UDWtype product.  This is just a variant of umul_ppmm.
> +
> +   3) udiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
> +   denominator) divides a UDWtype, composed by the UWtype integers
> +   HIGH_NUMERATOR and LOW_NUMERATOR, by DENOMINATOR and places the quotient
> +   in QUOTIENT and the remainder in REMAINDER.  HIGH_NUMERATOR must be less
> +   than DENOMINATOR for correct operation.  If, in addition, the most
> +   significant bit of DENOMINATOR must be 1, then the pre-processor symbol
> +   UDIV_NEEDS_NORMALIZATION is defined to 1.
> +
> +   4) sdiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
> +   denominator).  Like udiv_qrnnd but the numbers are signed.  The quotient
> +   is rounded towards 0.
> +
> +   5) count_leading_zeros(count, x) counts the number of zero-bits from the
> +   msb to the first nonzero bit in the UWtype X.  This is the number of
> +   steps X needs to be shifted left to set the msb.  Undefined for X == 0,
> +   unless the symbol COUNT_LEADING_ZEROS_0 is defined to some value.
> +
> +   6) count_trailing_zeros(count, x) like count_leading_zeros, but counts
> +   from the least significant end.
> +
> +   7) add_ssaaaa(high_sum, low_sum, high_addend_1, low_addend_1,
> +   high_addend_2, low_addend_2) adds two UWtype integers, composed by
> +   HIGH_ADDEND_1 and LOW_ADDEND_1, and HIGH_ADDEND_2 and LOW_ADDEND_2
> +   respectively.  The result is placed in HIGH_SUM and LOW_SUM.  Overflow
> +   (i.e. carry out) is not stored anywhere, and is lost.
> +
> +   8) sub_ddmmss(high_difference, low_difference, high_minuend, low_minuend,
> +   high_subtrahend, low_subtrahend) subtracts two two-word UWtype integers,
> +   composed by HIGH_MINUEND_1 and LOW_MINUEND_1, and HIGH_SUBTRAHEND_2 and
> +   LOW_SUBTRAHEND_2 respectively.  The result is placed in HIGH_DIFFERENCE
> +   and LOW_DIFFERENCE.  Overflow (i.e. carry out) is not stored anywhere,
> +   and is lost.
> +
> +   If any of these macros are left undefined for a particular CPU,
> +   C macros are used.  */
> +
> +/* The CPUs come in alphabetical order below.
> +
> +   Please add support for more CPUs here, or improve the current support
> +   for the CPUs below!
> +   (E.g. WE32100, IBM360.)  */
> +
> +/* Snipped per CPU support */
> +
> +/* If this machine has no inline assembler, use C macros.  */
> +
> +#if !defined (add_ssaaaa)
> +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
> +  do {									\
> +    UWtype __x;								\
> +    __x = (al) + (bl);							\
> +    (sh) = (ah) + (bh) + (__x < (al));					\
> +    (sl) = __x;								\
> +  } while (0)
> +#endif
> +
> +#if !defined (sub_ddmmss)
> +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
> +  do {									\
> +    UWtype __x;								\
> +    __x = (al) - (bl);							\
> +    (sh) = (ah) - (bh) - (__x > (al));					\
> +    (sl) = __x;								\
> +  } while (0)
> +#endif
> +
> +/* If we lack umul_ppmm but have smul_ppmm, define umul_ppmm in terms of
> +   smul_ppmm.  */
> +#if !defined (umul_ppmm) && defined (smul_ppmm)
> +#define umul_ppmm(w1, w0, u, v)						\
> +  do {									\
> +    UWtype __w1;							\
> +    UWtype __xm0 = (u), __xm1 = (v);					\
> +    smul_ppmm (__w1, w0, __xm0, __xm1);					\
> +    (w1) = __w1 + (-(__xm0 >> (W_TYPE_SIZE - 1)) & __xm1)		\
> +		+ (-(__xm1 >> (W_TYPE_SIZE - 1)) & __xm0);		\
> +  } while (0)
> +#endif
> +
> +/* If we still don't have umul_ppmm, define it using plain C.  */
> +#if !defined (umul_ppmm)
> +#define umul_ppmm(w1, w0, u, v)						\
> +  do {									\
> +    UWtype __x0, __x1, __x2, __x3;					\
> +    UHWtype __ul, __vl, __uh, __vh;					\
> +									\
> +    __ul = __ll_lowpart (u);						\
> +    __uh = __ll_highpart (u);						\
> +    __vl = __ll_lowpart (v);						\
> +    __vh = __ll_highpart (v);						\
> +									\
> +    __x0 = (UWtype) __ul * __vl;					\
> +    __x1 = (UWtype) __ul * __vh;					\
> +    __x2 = (UWtype) __uh * __vl;					\
> +    __x3 = (UWtype) __uh * __vh;					\
> +									\
> +    __x1 += __ll_highpart (__x0);/* this can't give carry */		\
> +    __x1 += __x2;		/* but this indeed can */		\
> +    if (__x1 < __x2)		/* did we get it? */			\
> +      __x3 += __ll_B;		/* yes, add it in the proper pos.  */	\
> +									\
> +    (w1) = __x3 + __ll_highpart (__x1);					\
> +    (w0) = __ll_lowpart (__x1) * __ll_B + __ll_lowpart (__x0);		\
> +  } while (0)
> +#endif
> +
> +#if !defined (__umulsidi3)
> +#define __umulsidi3(u, v) \
> +  ({DWunion __w;							\
> +    umul_ppmm (__w.s.high, __w.s.low, u, v);				\
> +    __w.ll; })
> +#endif
> +
> +/* Define this unconditionally, so it can be used for debugging.  */
> +#define __udiv_qrnnd_c(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)
> +
> +/* If the processor has no udiv_qrnnd but sdiv_qrnnd, go through
> +   __udiv_w_sdiv (defined in libgcc or elsewhere).  */
> +#if !defined (udiv_qrnnd) && defined (sdiv_qrnnd)
> +#define udiv_qrnnd(q, r, nh, nl, d) \
> +  do {									\
> +    USItype __r;							\
> +    (q) = __udiv_w_sdiv (&__r, nh, nl, d);				\
> +    (r) = __r;								\
> +  } while (0)
> +#endif
> +
> +/* If udiv_qrnnd was not defined for this processor, use __udiv_qrnnd_c.  */
> +#if !defined (udiv_qrnnd)
> +#define UDIV_NEEDS_NORMALIZATION 1
> +#define udiv_qrnnd __udiv_qrnnd_c
> +#endif
> +
> +#if !defined (count_leading_zeros)
> +#define count_leading_zeros(count, x) \
> +  do {									\
> +    UWtype __xr = (x);							\
> +    UWtype __a;								\
> +									\
> +    if (W_TYPE_SIZE <= 32)						\
> +      {									\
> +	__a = __xr < ((UWtype)1<<2*__BITS4)				\
> +	  ? (__xr < ((UWtype)1<<__BITS4) ? 0 : __BITS4)			\
> +	  : (__xr < ((UWtype)1<<3*__BITS4) ?  2*__BITS4 : 3*__BITS4);	\
> +      }									\
> +    else								\
> +      {									\
> +	for (__a = W_TYPE_SIZE - 8; __a > 0; __a -= 8)			\
> +	  if (((__xr >> __a) & 0xff) != 0)				\
> +	    break;							\
> +      }									\
> +									\
> +    (count) = W_TYPE_SIZE - (__clz_tab[__xr >> __a] + __a);		\
> +  } while (0)
> +#define COUNT_LEADING_ZEROS_0 W_TYPE_SIZE
> +#endif
> +
> +#if !defined (count_trailing_zeros)
> +/* Define count_trailing_zeros using count_leading_zeros.  The latter might be
> +   defined in asm, but if it is not, the C version above is good enough.  */
> +#define count_trailing_zeros(count, x) \
> +  do {									\
> +    UWtype __ctz_x = (x);						\
> +    UWtype __ctz_c;							\
> +    count_leading_zeros (__ctz_c, __ctz_x & -__ctz_x);			\
> +    (count) = W_TYPE_SIZE - 1 - __ctz_c;				\
> +  } while (0)
> +#endif
> +
> +#ifndef UDIV_NEEDS_NORMALIZATION
> +#define UDIV_NEEDS_NORMALIZATION 0
> +#endif
> diff --git a/arch/nios2/lib/math.h b/arch/nios2/lib/math.h
> deleted file mode 100644
> index f0aed8e..0000000
> --- a/arch/nios2/lib/math.h
> +++ /dev/null
> @@ -1,16 +0,0 @@
> -#define BITS_PER_UNIT	8
> -
> -typedef	 int HItype			__attribute__ ((mode (HI)));
> -typedef unsigned int UHItype		__attribute__ ((mode (HI)));
> -
> -typedef		 int SItype		__attribute__ ((mode (SI)));
> -typedef unsigned int USItype		__attribute__ ((mode (SI)));
> -
> -typedef int word_type			__attribute__ ((mode (__word__)));
> -
> -struct SIstruct {HItype low, high;};
> -
> -typedef union {
> -	struct SIstruct s;
> -	SItype ll;
> -} SIunion;
> diff --git a/arch/nios2/lib/mult.c b/arch/nios2/lib/mult.c
> deleted file mode 100644
> index ec8139e..0000000
> --- a/arch/nios2/lib/mult.c
> +++ /dev/null
> @@ -1,56 +0,0 @@
> -/*
> - * This file is part of GNU CC.
> - *
> - * GNU CC is free software; you can redistribute it and/or modify
> - * it under the terms of the GNU General Public License as published
> - * by the Free Software Foundation; either version 2, or (at your
> - * option) any later version.
> - *
> - * GNU CC is distributed in the hope that it will be useful,
> - * but WITHOUT ANY WARRANTY; without even the implied warranty of
> - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
> - * GNU General Public License for more details.
> - *
> - * You should have received a copy of the GNU General Public
> - * License along with GNU CC; see the file COPYING.  If not, write
> - * to the Free Software Foundation, 59 Temple Place - Suite 330,
> - * Boston, MA 02111-1307, USA.
> - */
> -
> -
> -#include <common.h>
> -
> -#if !defined(CONFIG_SYS_NIOS_MULT_HW) && !defined(CONFIG_SYS_NIOS_MULT_MSTEP)
> -
> -#include "math.h"
> -
> -USItype __mulsi3 (USItype a, USItype b)
> -{
> -	USItype c = 0;
> -
> -	while (a != 0) {
> -		if (a & 1)
> -			c += b;
> -		a >>= 1;
> -		b <<= 1;
> -	}
> -
> -	return c;
> -}
> -
> -
> -UHItype __mulhi3 (UHItype a, UHItype b)
> -{
> -	UHItype c = 0;
> -
> -	while (a != 0) {
> -		if (a & 1)
> -			c += b;
> -		a >>= 1;
> -		b <<= 1;
> -	}
> -
> -	return c;
> -}
> -
> -#endif /*!defined(CONFIG_SYS_NIOS_MULT_HW) && !defined(CONFIG_SYS_NIOS_MULT_MSTEP) */

[U-Boot] [PATCH] nios2: fix r15 issue for gcc4

[Mike Frysinger]

On Friday 14 May 2010 18:00:04 Thomas Chou wrote:
> The "-ffixed-r15" option doesn't work well for gcc4. Since we
> don't use gp for small data with option "-G0", we can use gp
> as global data pointer. This allows compiler to use r15. It
> is necessary for gcc4 to work properly.
> 
> Signed-off-by: Thomas Chou <thomas@wytron.com.tw>
> ---
>  arch/nios2/config.mk                 |    2 +-
>  arch/nios2/cpu/start.S               |    7 -------
>  arch/nios2/include/asm/global_data.h |    2 +-
>  3 files changed, 2 insertions(+), 9 deletions(-)

i think you also need to update examples/standalone/stubs.c

maybe also document things in README and doc/README.standalone ?
-mike
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 836 bytes
Desc: This is a digitally signed message part.
Url : http://lists.denx.de/pipermail/u-boot/attachments/20100519/11d0b8b8/attachment.pgp 

[U-Boot] [PATCH] nios2: fix r15 issue for gcc4

[Thomas Chou]

Mike Frysinger wrote:
> On Friday 14 May 2010 18:00:04 Thomas Chou wrote:
>> The "-ffixed-r15" option doesn't work well for gcc4. Since we
>> don't use gp for small data with option "-G0", we can use gp
>> as global data pointer. This allows compiler to use r15. It
>> is necessary for gcc4 to work properly.
>>
>> Signed-off-by: Thomas Chou <thomas@wytron.com.tw>
>> ---
>>  arch/nios2/config.mk                 |    2 +-
>>  arch/nios2/cpu/start.S               |    7 -------
>>  arch/nios2/include/asm/global_data.h |    2 +-
>>  3 files changed, 2 insertions(+), 9 deletions(-)
> 
> i think you also need to update examples/standalone/stubs.c
> 
> maybe also document things in README and doc/README.standalone ?
> -mike

Dear Mike,

Thank you very mcuh.

The nios2 gd usage was not documented. I will add it to README and 
doc/README.standalone. I will update examples/standalone/stubs.c, too.

Best regards,
Thomas

[U-Boot] [PATCH] nios2: allow STANDALONE_LOAD_ADDR overriding

[Thomas Chou]

This patch allows users to override default STANDALONE_LOAD_ADDR.
The gcclibdir path was duplicated in the standalone Makefile and
can be removed.

Signed-off-by: Thomas Chou <thomas@wytron.com.tw>
---
 arch/nios2/config.mk |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/arch/nios2/config.mk b/arch/nios2/config.mk
index 6789038..793cc43 100644
--- a/arch/nios2/config.mk
+++ b/arch/nios2/config.mk
@@ -24,7 +24,7 @@
 
 CROSS_COMPILE ?= nios2-elf-
 
-STANDALONE_LOAD_ADDR = 0x02000000 -L $(gcclibdir)
+STANDALONE_LOAD_ADDR ?= 0x02000000
 
 PLATFORM_CPPFLAGS += -DCONFIG_NIOS2 -D__NIOS2__
 PLATFORM_CPPFLAGS += -G0
-- 
1.7.1.86.g0e460

[U-Boot] [PATCH] nios2: allow STANDALONE_LOAD_ADDR overriding

[Scott McNutt]

Applied to:
    git://git.denx.de/u-boot-nios.git next

Thanks,
--Scott

Thomas Chou wrote:
> This patch allows users to override default STANDALONE_LOAD_ADDR.
> The gcclibdir path was duplicated in the standalone Makefile and
> can be removed.
> 
> Signed-off-by: Thomas Chou <thomas@wytron.com.tw>
> ---
>  arch/nios2/config.mk |    2 +-
>  1 files changed, 1 insertions(+), 1 deletions(-)
> 
> diff --git a/arch/nios2/config.mk b/arch/nios2/config.mk
> index 6789038..793cc43 100644
> --- a/arch/nios2/config.mk
> +++ b/arch/nios2/config.mk
> @@ -24,7 +24,7 @@
>  
>  CROSS_COMPILE ?= nios2-elf-
>  
> -STANDALONE_LOAD_ADDR = 0x02000000 -L $(gcclibdir)
> +STANDALONE_LOAD_ADDR ?= 0x02000000
>  
>  PLATFORM_CPPFLAGS += -DCONFIG_NIOS2 -D__NIOS2__
>  PLATFORM_CPPFLAGS += -G0

[U-Boot] [PATCH v2] nios2: fix r15 issue for gcc4

[Thomas Chou]

The "-ffixed-r15" option doesn't work well for gcc4. Since we
don't use gp for small data with option "-G0", we can use gp
as global data pointer. This allows compiler to use r15. It
is necessary for gcc4 to work properly.

Signed-off-by: Thomas Chou <thomas@wytron.com.tw>
---
v2: update standalone stubs and doc.

 README                               |    8 ++++++++
 arch/nios2/config.mk                 |    2 +-
 arch/nios2/cpu/start.S               |    7 -------
 arch/nios2/include/asm/global_data.h |    2 +-
 doc/README.standalone                |   13 +++++++------
 examples/standalone/stubs.c          |    6 +++---
 6 files changed, 20 insertions(+), 18 deletions(-)

diff --git a/README b/README
index 81692c0..acb3308 100644
--- a/README
+++ b/README
@@ -4023,6 +4023,14 @@ On ARM, the following registers are used:
 
     ==> U-Boot will use R8 to hold a pointer to the global data
 
+On Nios II, the ABI is documented here:
+	http://www.altera.com/literature/hb/nios2/n2cpu_nii51016.pdf
+
+    ==> U-Boot will use gp to hold a pointer to the global data
+
+    Note: on Nios II, we give "-G0" option to gcc and don't use gp
+    to access small data sections, so gp is free.
+
 NOTE: DECLARE_GLOBAL_DATA_PTR must be used with file-global scope,
 or current versions of GCC may "optimize" the code too much.
 
diff --git a/arch/nios2/config.mk b/arch/nios2/config.mk
index 8e5d6ef..6789038 100644
--- a/arch/nios2/config.mk
+++ b/arch/nios2/config.mk
@@ -27,6 +27,6 @@ CROSS_COMPILE ?= nios2-elf-
 STANDALONE_LOAD_ADDR = 0x02000000 -L $(gcclibdir)
 
 PLATFORM_CPPFLAGS += -DCONFIG_NIOS2 -D__NIOS2__
-PLATFORM_CPPFLAGS += -ffixed-r15 -G0
+PLATFORM_CPPFLAGS += -G0
 
 LDSCRIPT ?= $(SRCTREE)/$(CPUDIR)/u-boot.lds
diff --git a/arch/nios2/cpu/start.S b/arch/nios2/cpu/start.S
index d1016ea..76d3b52 100644
--- a/arch/nios2/cpu/start.S
+++ b/arch/nios2/cpu/start.S
@@ -113,13 +113,6 @@ _cur:	movhi	r5, %hi(_cur - _start)
 	 bne	r5, r6, 4b
 5:
 
-	/* GLOBAL POINTER -- the global pointer is used to reference
-	 * "small data" (see -G switch). The linker script must
-	 * provide the gp address.
-	 */
-	 movhi	gp, %hi(_gp)
-	 ori	gp, gp, %lo(_gp)
-
 	/* JUMP TO RELOC ADDR */
 	movhi	r4, %hi(_reloc)
 	ori	r4, r4, %lo(_reloc)
diff --git a/arch/nios2/include/asm/global_data.h b/arch/nios2/include/asm/global_data.h
index 34aa962..f1b3482 100644
--- a/arch/nios2/include/asm/global_data.h
+++ b/arch/nios2/include/asm/global_data.h
@@ -48,6 +48,6 @@ typedef	struct	global_data {
 #define	GD_FLG_LOGINIT	0x00020		/* Log Buffer has been initialized	*/
 #define GD_FLG_DISABLE_CONSOLE	0x00040		/* Disable console (in & out)	 */
 
-#define DECLARE_GLOBAL_DATA_PTR     register gd_t *gd asm ("r15")
+#define DECLARE_GLOBAL_DATA_PTR     register gd_t *gd asm ("gp")
 
 #endif /* __ASM_NIOS2_GLOBALDATA_H_ */
diff --git a/doc/README.standalone b/doc/README.standalone
index 885c92f..6381087 100644
--- a/doc/README.standalone
+++ b/doc/README.standalone
@@ -19,12 +19,12 @@ Design Notes on Exporting U-Boot Functions to Standalone Applications:
    thus the compiler cannot perform type checks on these assignments.
 
 2. The pointer to the jump table is passed to the application in a
-   machine-dependent way. PowerPC, ARM, MIPS and Blackfin architectures
-   use a dedicated register to hold the pointer to the 'global_data'
-   structure: r2 on PowerPC, r8 on ARM, k0 on MIPS, and P3 on Blackfin.
-   The x86 architecture does not use such a register; instead, the
-   pointer to the 'global_data' structure is passed as 'argv[-1]'
-   pointer.
+   machine-dependent way. PowerPC, ARM, MIPS, Blackfin and Nios II
+   architectures use a dedicated register to hold the pointer to the
+   'global_data' structure: r2 on PowerPC, r8 on ARM, k0 on MIPS,
+   P3 on Blackfin and gp on Nios II. The x86 architecture does not
+   use such a register; instead, the pointer to the 'global_data'
+   structure is passed as 'argv[-1]' pointer.
 
    The application can access the 'global_data' structure in the same
    way as U-Boot does:
@@ -56,6 +56,7 @@ Design Notes on Exporting U-Boot Functions to Standalone Applications:
 	ARM		0x0c100000	0x0c100000
 	MIPS		0x80200000	0x80200000
 	Blackfin	0x00001000	0x00001000
+	Nios II		0x02000000	0x02000000
 
    For example, the "hello world" application may be loaded and
    executed on a PowerPC board with the following commands:
diff --git a/examples/standalone/stubs.c b/examples/standalone/stubs.c
index ce3371d..0187708 100644
--- a/examples/standalone/stubs.c
+++ b/examples/standalone/stubs.c
@@ -84,7 +84,7 @@ gd_t *global_data;
 	: : "i"(offsetof(gd_t, jt)), "i"(XF_ ## x) : "r0");
 #elif defined(CONFIG_NIOS2)
 /*
- * r15 holds the pointer to the global_data, r8 is call-clobbered
+ * gp holds the pointer to the global_data, r8 is call-clobbered
  */
 #define EXPORT_FUNC(x) \
 	asm volatile (			\
@@ -92,11 +92,11 @@ gd_t *global_data;
 #x ":\n"				\
 "	movhi	r8, %%hi(%0)\n"		\
 "	ori	r8, r0, %%lo(%0)\n"	\
-"	add	r8, r8, r15\n"		\
+"	add	r8, r8, gp\n"		\
 "	ldw	r8, 0(r8)\n"		\
 "	ldw	r8, %1(r8)\n"		\
 "	jmp	r8\n"			\
-	: : "i"(offsetof(gd_t, jt)), "i"(XF_ ## x * sizeof(void *)) : "r15");
+	: : "i"(offsetof(gd_t, jt)), "i"(XF_ ## x * sizeof(void *)) : "gp");
 #elif defined(CONFIG_M68K)
 /*
  * d7 holds the pointer to the global_data, a0 is a call-clobbered
-- 
1.7.1.86.g0e460

[U-Boot] [PATCH v2] nios2: fix r15 issue for gcc4

[Scott McNutt]

Applied to:
    git://git.denx.de/u-boot-nios.git next

Thanks,
--Scott

Thomas Chou wrote:
> The "-ffixed-r15" option doesn't work well for gcc4. Since we
> don't use gp for small data with option "-G0", we can use gp
> as global data pointer. This allows compiler to use r15. It
> is necessary for gcc4 to work properly.
> 
> Signed-off-by: Thomas Chou <thomas@wytron.com.tw>
> ---
> v2: update standalone stubs and doc.
> 
>  README                               |    8 ++++++++
>  arch/nios2/config.mk                 |    2 +-
>  arch/nios2/cpu/start.S               |    7 -------
>  arch/nios2/include/asm/global_data.h |    2 +-
>  doc/README.standalone                |   13 +++++++------
>  examples/standalone/stubs.c          |    6 +++---
>  6 files changed, 20 insertions(+), 18 deletions(-)
> 
> diff --git a/README b/README
> index 81692c0..acb3308 100644
> --- a/README
> +++ b/README
> @@ -4023,6 +4023,14 @@ On ARM, the following registers are used:
>  
>      ==> U-Boot will use R8 to hold a pointer to the global data
>  
> +On Nios II, the ABI is documented here:
> +	http://www.altera.com/literature/hb/nios2/n2cpu_nii51016.pdf
> +
> +    ==> U-Boot will use gp to hold a pointer to the global data
> +
> +    Note: on Nios II, we give "-G0" option to gcc and don't use gp
> +    to access small data sections, so gp is free.
> +
>  NOTE: DECLARE_GLOBAL_DATA_PTR must be used with file-global scope,
>  or current versions of GCC may "optimize" the code too much.
>  
> diff --git a/arch/nios2/config.mk b/arch/nios2/config.mk
> index 8e5d6ef..6789038 100644
> --- a/arch/nios2/config.mk
> +++ b/arch/nios2/config.mk
> @@ -27,6 +27,6 @@ CROSS_COMPILE ?= nios2-elf-
>  STANDALONE_LOAD_ADDR = 0x02000000 -L $(gcclibdir)
>  
>  PLATFORM_CPPFLAGS += -DCONFIG_NIOS2 -D__NIOS2__
> -PLATFORM_CPPFLAGS += -ffixed-r15 -G0
> +PLATFORM_CPPFLAGS += -G0
>  
>  LDSCRIPT ?= $(SRCTREE)/$(CPUDIR)/u-boot.lds
> diff --git a/arch/nios2/cpu/start.S b/arch/nios2/cpu/start.S
> index d1016ea..76d3b52 100644
> --- a/arch/nios2/cpu/start.S
> +++ b/arch/nios2/cpu/start.S
> @@ -113,13 +113,6 @@ _cur:	movhi	r5, %hi(_cur - _start)
>  	 bne	r5, r6, 4b
>  5:
>  
> -	/* GLOBAL POINTER -- the global pointer is used to reference
> -	 * "small data" (see -G switch). The linker script must
> -	 * provide the gp address.
> -	 */
> -	 movhi	gp, %hi(_gp)
> -	 ori	gp, gp, %lo(_gp)
> -
>  	/* JUMP TO RELOC ADDR */
>  	movhi	r4, %hi(_reloc)
>  	ori	r4, r4, %lo(_reloc)
> diff --git a/arch/nios2/include/asm/global_data.h b/arch/nios2/include/asm/global_data.h
> index 34aa962..f1b3482 100644
> --- a/arch/nios2/include/asm/global_data.h
> +++ b/arch/nios2/include/asm/global_data.h
> @@ -48,6 +48,6 @@ typedef	struct	global_data {
>  #define	GD_FLG_LOGINIT	0x00020		/* Log Buffer has been initialized	*/
>  #define GD_FLG_DISABLE_CONSOLE	0x00040		/* Disable console (in & out)	 */
>  
> -#define DECLARE_GLOBAL_DATA_PTR     register gd_t *gd asm ("r15")
> +#define DECLARE_GLOBAL_DATA_PTR     register gd_t *gd asm ("gp")
>  
>  #endif /* __ASM_NIOS2_GLOBALDATA_H_ */
> diff --git a/doc/README.standalone b/doc/README.standalone
> index 885c92f..6381087 100644
> --- a/doc/README.standalone
> +++ b/doc/README.standalone
> @@ -19,12 +19,12 @@ Design Notes on Exporting U-Boot Functions to Standalone Applications:
>     thus the compiler cannot perform type checks on these assignments.
>  
>  2. The pointer to the jump table is passed to the application in a
> -   machine-dependent way. PowerPC, ARM, MIPS and Blackfin architectures
> -   use a dedicated register to hold the pointer to the 'global_data'
> -   structure: r2 on PowerPC, r8 on ARM, k0 on MIPS, and P3 on Blackfin.
> -   The x86 architecture does not use such a register; instead, the
> -   pointer to the 'global_data' structure is passed as 'argv[-1]'
> -   pointer.
> +   machine-dependent way. PowerPC, ARM, MIPS, Blackfin and Nios II
> +   architectures use a dedicated register to hold the pointer to the
> +   'global_data' structure: r2 on PowerPC, r8 on ARM, k0 on MIPS,
> +   P3 on Blackfin and gp on Nios II. The x86 architecture does not
> +   use such a register; instead, the pointer to the 'global_data'
> +   structure is passed as 'argv[-1]' pointer.
>  
>     The application can access the 'global_data' structure in the same
>     way as U-Boot does:
> @@ -56,6 +56,7 @@ Design Notes on Exporting U-Boot Functions to Standalone Applications:
>  	ARM		0x0c100000	0x0c100000
>  	MIPS		0x80200000	0x80200000
>  	Blackfin	0x00001000	0x00001000
> +	Nios II		0x02000000	0x02000000
>  
>     For example, the "hello world" application may be loaded and
>     executed on a PowerPC board with the following commands:
> diff --git a/examples/standalone/stubs.c b/examples/standalone/stubs.c
> index ce3371d..0187708 100644
> --- a/examples/standalone/stubs.c
> +++ b/examples/standalone/stubs.c
> @@ -84,7 +84,7 @@ gd_t *global_data;
>  	: : "i"(offsetof(gd_t, jt)), "i"(XF_ ## x) : "r0");
>  #elif defined(CONFIG_NIOS2)
>  /*
> - * r15 holds the pointer to the global_data, r8 is call-clobbered
> + * gp holds the pointer to the global_data, r8 is call-clobbered
>   */
>  #define EXPORT_FUNC(x) \
>  	asm volatile (			\
> @@ -92,11 +92,11 @@ gd_t *global_data;
>  #x ":\n"				\
>  "	movhi	r8, %%hi(%0)\n"		\
>  "	ori	r8, r0, %%lo(%0)\n"	\
> -"	add	r8, r8, r15\n"		\
> +"	add	r8, r8, gp\n"		\
>  "	ldw	r8, 0(r8)\n"		\
>  "	ldw	r8, %1(r8)\n"		\
>  "	jmp	r8\n"			\
> -	: : "i"(offsetof(gd_t, jt)), "i"(XF_ ## x * sizeof(void *)) : "r15");
> +	: : "i"(offsetof(gd_t, jt)), "i"(XF_ ## x * sizeof(void *)) : "gp");
>  #elif defined(CONFIG_M68K)
>  /*
>   * d7 holds the pointer to the global_data, a0 is a call-clobbered