diff --git a/arch/powerpc/math-emu/sfp-machine.h b/arch/powerpc/include/asm/sfp-machine.h
similarity index 83%
rename from arch/powerpc/math-emu/sfp-machine.h
rename to arch/powerpc/include/asm/sfp-machine.h
index 4b17d83..ced34f1 100644
--- a/arch/powerpc/math-emu/sfp-machine.h
+++ b/arch/powerpc/include/asm/sfp-machine.h
@@ -79,27 +79,44 @@
  * #define _FP_DIV_MEAT_D(R,X,Y)   _FP_DIV_MEAT_2_udiv_64(D,R,X,Y)
  */
 
-#define _FP_MUL_MEAT_S(R,X,Y)   _FP_MUL_MEAT_1_wide(S,R,X,Y,umul_ppmm)
-#define _FP_MUL_MEAT_D(R,X,Y)   _FP_MUL_MEAT_2_wide(D,R,X,Y,umul_ppmm)
+#define _FP_MUL_MEAT_S(R,X,Y)   _FP_MUL_MEAT_1_wide(_FP_WFRACBITS_S,R,X,Y,umul_ppmm)
+#define _FP_MUL_MEAT_D(R,X,Y)   _FP_MUL_MEAT_2_wide(_FP_WFRACBITS_D,R,X,Y,umul_ppmm)
 
-#define _FP_DIV_MEAT_S(R,X,Y)   _FP_DIV_MEAT_1_udiv(S,R,X,Y)
-#define _FP_DIV_MEAT_D(R,X,Y)   _FP_DIV_MEAT_2_udiv_64(D,R,X,Y)
+#define _FP_DIV_MEAT_S(R,X,Y)	_FP_DIV_MEAT_1_udiv(S,R,X,Y)
+#define _FP_DIV_MEAT_D(R,X,Y)	_FP_DIV_MEAT_2_udiv(D,R,X,Y)
 
 /* These macros define what NaN looks like. They're supposed to expand to
  * a comma-separated set of 32bit unsigned ints that encode NaN.
  */
-#define _FP_NANFRAC_S		_FP_QNANBIT_S
-#define _FP_NANFRAC_D		_FP_QNANBIT_D, 0
-#define _FP_NANFRAC_Q           _FP_QNANBIT_Q, 0, 0, 0
+#define _FP_NANFRAC_S		((_FP_QNANBIT_S << 1) - 1)
+#define _FP_NANFRAC_D		((_FP_QNANBIT_D << 1) - 1), -1
+#define _FP_NANFRAC_Q		((_FP_QNANBIT_Q << 1) - 1), -1, -1, -1
+#define _FP_NANSIGN_S		0
+#define _FP_NANSIGN_D		0
+#define _FP_NANSIGN_Q		0
 
 #define _FP_KEEPNANFRACP 1
 
+/* Exception flags.  We use the bit positions of the appropriate bits
+   in the FPSCR, which also correspond to the FE_* bits.  This makes
+   everything easier ;-).  */
+#define FP_EX_INVALID         (1 << (31 - 2))
+#define FP_EX_INVALID_SNAN	EFLAG_VXSNAN
+#define FP_EX_INVALID_ISI	EFLAG_VXISI
+#define FP_EX_INVALID_IDI	EFLAG_VXIDI
+#define FP_EX_INVALID_ZDZ	EFLAG_VXZDZ
+#define FP_EX_INVALID_IMZ	EFLAG_VXIMZ
+#define FP_EX_OVERFLOW        (1 << (31 - 3))
+#define FP_EX_UNDERFLOW       (1 << (31 - 4))
+#define FP_EX_DIVZERO         (1 << (31 - 5))
+#define FP_EX_INEXACT         (1 << (31 - 6))
+
 /* This macro appears to be called when both X and Y are NaNs, and
  * has to choose one and copy it to R. i386 goes for the larger of the
  * two, sparc64 just picks Y. I don't understand this at all so I'll
  * go with sparc64 because it's shorter :->   -- PMM
  */
-#define _FP_CHOOSENAN(fs, wc, R, X, Y)			\
+#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP)		\
   do {							\
     R##_s = Y##_s;					\
     _FP_FRAC_COPY_##wc(R,Y);				\
@@ -107,62 +124,6 @@
   } while (0)
 
 
-extern void fp_unpack_d(long *, unsigned long *, unsigned long *,
-			long *, long *, void *);
-extern int  fp_pack_d(void *, long, unsigned long, unsigned long, long, long);
-extern int  fp_pack_ds(void *, long, unsigned long, unsigned long, long, long);
-
-#define __FP_UNPACK_RAW_1(fs, X, val)			\
-  do {							\
-    union _FP_UNION_##fs *_flo =			\
-    	(union _FP_UNION_##fs *)val;			\
-							\
-    X##_f = _flo->bits.frac;				\
-    X##_e = _flo->bits.exp;				\
-    X##_s = _flo->bits.sign;				\
-  } while (0)
-
-#define __FP_UNPACK_RAW_2(fs, X, val)			\
-  do {							\
-    union _FP_UNION_##fs *_flo =			\
-    	(union _FP_UNION_##fs *)val;			\
-							\
-    X##_f0 = _flo->bits.frac0;				\
-    X##_f1 = _flo->bits.frac1;				\
-    X##_e  = _flo->bits.exp;				\
-    X##_s  = _flo->bits.sign;				\
-  } while (0)
-
-#define __FP_UNPACK_S(X,val)		\
-  do {					\
-    __FP_UNPACK_RAW_1(S,X,val);		\
-    _FP_UNPACK_CANONICAL(S,1,X);	\
-  } while (0)
-
-#define __FP_UNPACK_D(X,val)		\
-	fp_unpack_d(&X##_s, &X##_f1, &X##_f0, &X##_e, &X##_c, val)
-
-#define __FP_PACK_RAW_1(fs, val, X)			\
-  do {							\
-    union _FP_UNION_##fs *_flo =			\
-    	(union _FP_UNION_##fs *)val;			\
-							\
-    _flo->bits.frac = X##_f;				\
-    _flo->bits.exp  = X##_e;				\
-    _flo->bits.sign = X##_s;				\
-  } while (0)
-
-#define __FP_PACK_RAW_2(fs, val, X)			\
-  do {							\
-    union _FP_UNION_##fs *_flo =			\
-    	(union _FP_UNION_##fs *)val;			\
-							\
-    _flo->bits.frac0 = X##_f0;				\
-    _flo->bits.frac1 = X##_f1;				\
-    _flo->bits.exp   = X##_e;				\
-    _flo->bits.sign  = X##_s;				\
-  } while (0)
-
 #include <linux/kernel.h>
 #include <linux/sched.h>
 
@@ -182,15 +143,30 @@
 #define __FP_PACK_S(val,X)			\
 ({  int __exc = _FP_PACK_CANONICAL(S,1,X);	\
     if(!__exc || !__FPU_TRAP_P(__exc))		\
-        __FP_PACK_RAW_1(S,val,X);		\
+        _FP_PACK_RAW_1_P(S,val,X);		\
     __exc;					\
 })
 
 #define __FP_PACK_D(val,X)			\
-	fp_pack_d(val, X##_s, X##_f1, X##_f0, X##_e, X##_c)
+   do {									\
+	_FP_PACK_CANONICAL(D, 2, X);					\
+	if (!FP_CUR_EXCEPTIONS || !__FPU_TRAP_P(FP_CUR_EXCEPTIONS))	\
+		_FP_PACK_RAW_2_P(D, val, X);				\
+   } while (0)
 
-#define __FP_PACK_DS(val,X)			\
-	fp_pack_ds(val, X##_s, X##_f1, X##_f0, X##_e, X##_c)
+#define __FP_PACK_DS(val,X)							\
+   do {										\
+	   FP_DECL_S(__X);							\
+	   FP_CONV(S, D, 1, 2, __X, X);						\
+	   _FP_PACK_CANONICAL(S, 1, __X);					\
+	   if (!FP_CUR_EXCEPTIONS || !__FPU_TRAP_P(FP_CUR_EXCEPTIONS)) {	\
+		   _FP_UNPACK_CANONICAL(S, 1, __X);				\
+		   FP_CONV(D, S, 2, 1, X, __X);					\
+		   _FP_PACK_CANONICAL(D, 2, X);					\
+		   if (!FP_CUR_EXCEPTIONS || !__FPU_TRAP_P(FP_CUR_EXCEPTIONS))	\
+		   _FP_PACK_RAW_2_P(D, val, X);					\
+	   }									\
+   } while (0)
 
 /* Obtain the current rounding mode. */
 #define FP_ROUNDMODE			\
diff --git a/arch/powerpc/math-emu/Makefile b/arch/powerpc/math-emu/Makefile
index 29bc912..03aa98d 100644
--- a/arch/powerpc/math-emu/Makefile
+++ b/arch/powerpc/math-emu/Makefile
@@ -4,13 +4,14 @@
 obj-$(CONFIG_MATH_EMULATION)	+= fabs.o fadd.o fadds.o fcmpo.o fcmpu.o \
 					fctiw.o fctiwz.o fdiv.o fdivs.o \
 					fmadd.o fmadds.o fmsub.o fmsubs.o \
-					fmul.o fmuls.o fnabs.o fneg.o types.o \
+					fmul.o fmuls.o fnabs.o fneg.o \
 					fnmadd.o fnmadds.o fnmsub.o fnmsubs.o \
 					fres.o frsp.o frsqrte.o fsel.o lfs.o \
 					fsqrt.o	fsqrts.o fsub.o fsubs.o \
 					mcrfs.o mffs.o mtfsb0.o mtfsb1.o \
-					mtfsf.o mtfsfi.o stfiwx.o stfs.o \
-					udivmodti4.o
+					mtfsf.o mtfsfi.o stfiwx.o stfs.o
 
 CFLAGS_fabs.o = -fno-builtin-fabs
 CFLAGS_math.o = -fno-builtin-fabs
+
+EXTRA_CFLAGS = -I. -Iinclude/math-emu -w
diff --git a/arch/powerpc/math-emu/double.h b/arch/powerpc/math-emu/double.h
deleted file mode 100644
index ffba8b6..0000000
--- a/arch/powerpc/math-emu/double.h
+++ /dev/null
@@ -1,129 +0,0 @@
-/*
- * Definitions for IEEE Double Precision
- */
-
-#if _FP_W_TYPE_SIZE < 32
-#error "Here's a nickel kid.  Go buy yourself a real computer."
-#endif
-
-#if _FP_W_TYPE_SIZE < 64
-#define _FP_FRACTBITS_D		(2 * _FP_W_TYPE_SIZE)
-#else
-#define _FP_FRACTBITS_D		_FP_W_TYPE_SIZE
-#endif
-
-#define _FP_FRACBITS_D		53
-#define _FP_FRACXBITS_D		(_FP_FRACTBITS_D - _FP_FRACBITS_D)
-#define _FP_WFRACBITS_D		(_FP_WORKBITS + _FP_FRACBITS_D)
-#define _FP_WFRACXBITS_D	(_FP_FRACTBITS_D - _FP_WFRACBITS_D)
-#define _FP_EXPBITS_D		11
-#define _FP_EXPBIAS_D		1023
-#define _FP_EXPMAX_D		2047
-
-#define _FP_QNANBIT_D		\
-	((_FP_W_TYPE)1 << ((_FP_FRACBITS_D-2) % _FP_W_TYPE_SIZE))
-#define _FP_IMPLBIT_D		\
-	((_FP_W_TYPE)1 << ((_FP_FRACBITS_D-1) % _FP_W_TYPE_SIZE))
-#define _FP_OVERFLOW_D		\
-	((_FP_W_TYPE)1 << (_FP_WFRACBITS_D % _FP_W_TYPE_SIZE))
-
-#if _FP_W_TYPE_SIZE < 64
-
-union _FP_UNION_D
-{
-  double flt;
-  struct {
-#if __BYTE_ORDER == __BIG_ENDIAN
-    unsigned sign  : 1;
-    unsigned exp   : _FP_EXPBITS_D;
-    unsigned frac1 : _FP_FRACBITS_D - (_FP_IMPLBIT_D != 0) - _FP_W_TYPE_SIZE;
-    unsigned frac0 : _FP_W_TYPE_SIZE;
-#else
-    unsigned frac0 : _FP_W_TYPE_SIZE;
-    unsigned frac1 : _FP_FRACBITS_D - (_FP_IMPLBIT_D != 0) - _FP_W_TYPE_SIZE;
-    unsigned exp   : _FP_EXPBITS_D;
-    unsigned sign  : 1;
-#endif
-  } bits __attribute__((packed));
-};
-
-#define FP_DECL_D(X)		_FP_DECL(2,X)
-#define FP_UNPACK_RAW_D(X,val)	_FP_UNPACK_RAW_2(D,X,val)
-#define FP_PACK_RAW_D(val,X)	_FP_PACK_RAW_2(D,val,X)
-
-#define FP_UNPACK_D(X,val)		\
-  do {					\
-    _FP_UNPACK_RAW_2(D,X,val);		\
-    _FP_UNPACK_CANONICAL(D,2,X);	\
-  } while (0)
-
-#define FP_PACK_D(val,X)		\
-  do {					\
-    _FP_PACK_CANONICAL(D,2,X);		\
-    _FP_PACK_RAW_2(D,val,X);		\
-  } while (0)
-
-#define FP_NEG_D(R,X)		_FP_NEG(D,2,R,X)
-#define FP_ADD_D(R,X,Y)		_FP_ADD(D,2,R,X,Y)
-#define FP_SUB_D(R,X,Y)		_FP_SUB(D,2,R,X,Y)
-#define FP_MUL_D(R,X,Y)		_FP_MUL(D,2,R,X,Y)
-#define FP_DIV_D(R,X,Y)		_FP_DIV(D,2,R,X,Y)
-#define FP_SQRT_D(R,X)		_FP_SQRT(D,2,R,X)
-
-#define FP_CMP_D(r,X,Y,un)	_FP_CMP(D,2,r,X,Y,un)
-#define FP_CMP_EQ_D(r,X,Y)	_FP_CMP_EQ(D,2,r,X,Y)
-
-#define FP_TO_INT_D(r,X,rsz,rsg)  _FP_TO_INT(D,2,r,X,rsz,rsg)
-#define FP_FROM_INT_D(X,r,rs,rt)  _FP_FROM_INT(D,2,X,r,rs,rt)
-
-#else
-
-union _FP_UNION_D
-{
-  double flt;
-  struct {
-#if __BYTE_ORDER == __BIG_ENDIAN
-    unsigned sign : 1;
-    unsigned exp  : _FP_EXPBITS_D;
-    unsigned long frac : _FP_FRACBITS_D - (_FP_IMPLBIT_D != 0);
-#else
-    unsigned long frac : _FP_FRACBITS_D - (_FP_IMPLBIT_D != 0);
-    unsigned exp  : _FP_EXPBITS_D;
-    unsigned sign : 1;
-#endif
-  } bits __attribute__((packed));
-};
-
-#define FP_DECL_D(X)		_FP_DECL(1,X)
-#define FP_UNPACK_RAW_D(X,val)	_FP_UNPACK_RAW_1(D,X,val)
-#define FP_PACK_RAW_D(val,X)	_FP_PACK_RAW_1(D,val,X)
-
-#define FP_UNPACK_D(X,val)		\
-  do {					\
-    _FP_UNPACK_RAW_1(D,X,val);		\
-    _FP_UNPACK_CANONICAL(D,1,X);	\
-  } while (0)
-
-#define FP_PACK_D(val,X)		\
-  do {					\
-    _FP_PACK_CANONICAL(D,1,X);		\
-    _FP_PACK_RAW_1(D,val,X);		\
-  } while (0)
-
-#define FP_NEG_D(R,X)		_FP_NEG(D,1,R,X)
-#define FP_ADD_D(R,X,Y)		_FP_ADD(D,1,R,X,Y)
-#define FP_SUB_D(R,X,Y)		_FP_SUB(D,1,R,X,Y)
-#define FP_MUL_D(R,X,Y)		_FP_MUL(D,1,R,X,Y)
-#define FP_DIV_D(R,X,Y)		_FP_DIV(D,1,R,X,Y)
-#define FP_SQRT_D(R,X)		_FP_SQRT(D,1,R,X)
-
-/* The implementation of _FP_MUL_D and _FP_DIV_D should be chosen by
-   the target machine.  */
-
-#define FP_CMP_D(r,X,Y,un)	_FP_CMP(D,1,r,X,Y,un)
-#define FP_CMP_EQ_D(r,X,Y)	_FP_CMP_EQ(D,1,r,X,Y)
-
-#define FP_TO_INT_D(r,X,rsz,rsg)  _FP_TO_INT(D,1,r,X,rsz,rsg)
-#define FP_FROM_INT_D(X,r,rs,rt)  _FP_FROM_INT(D,1,X,r,rs,rt)
-
-#endif /* W_TYPE_SIZE < 64 */
diff --git a/arch/powerpc/math-emu/fadd.c b/arch/powerpc/math-emu/fadd.c
index 7befbbf..04d3b4a 100644
--- a/arch/powerpc/math-emu/fadd.c
+++ b/arch/powerpc/math-emu/fadd.c
@@ -2,8 +2,9 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
 
 int
 fadd(void *frD, void *frA, void *frB)
@@ -11,28 +12,28 @@
 	FP_DECL_D(A);
 	FP_DECL_D(B);
 	FP_DECL_D(R);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
 	printk("B: %ld %lu %lu %ld (%ld)\n", B_s, B_f1, B_f0, B_e, B_c);
 #endif
 
-	if (A_s != B_s && A_c == FP_CLS_INF && B_c == FP_CLS_INF)
-		ret |= EFLAG_VXISI;
-
 	FP_ADD_D(R, A, B);
 
 #ifdef DEBUG
 	printk("D: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_D(frD, R));
+	__FP_PACK_D(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fadds.c b/arch/powerpc/math-emu/fadds.c
index 2b346b3..5930f40 100644
--- a/arch/powerpc/math-emu/fadds.c
+++ b/arch/powerpc/math-emu/fadds.c
@@ -2,9 +2,10 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
-#include "single.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
 
 int
 fadds(void *frD, void *frA, void *frB)
@@ -12,28 +13,27 @@
 	FP_DECL_D(A);
 	FP_DECL_D(B);
 	FP_DECL_D(R);
-	int ret = 0;
+	FP_DECL_EX;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
 	printk("B: %ld %lu %lu %ld (%ld)\n", B_s, B_f1, B_f0, B_e, B_c);
 #endif
 
-	if (A_s != B_s && A_c == FP_CLS_INF && B_c == FP_CLS_INF)
-		ret |= EFLAG_VXISI;
-
 	FP_ADD_D(R, A, B);
 
 #ifdef DEBUG
 	printk("D: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_DS(frD, R));
+	__FP_PACK_DS(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fcmpo.c b/arch/powerpc/math-emu/fcmpo.c
index 36d6890..b5dc449 100644
--- a/arch/powerpc/math-emu/fcmpo.c
+++ b/arch/powerpc/math-emu/fcmpo.c
@@ -2,14 +2,16 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
 
 int
 fcmpo(u32 *ccr, int crfD, void *frA, void *frB)
 {
 	FP_DECL_D(A);
 	FP_DECL_D(B);
+	FP_DECL_EX;
 	int code[4] = { (1 << 3), (1 << 1), (1 << 2), (1 << 0) };
 	long cmp;
 	int ret = 0;
@@ -18,8 +20,8 @@
 	printk("%s: %p (%08x) %d %p %p\n", __func__, ccr, *ccr, crfD, frA, frB);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
diff --git a/arch/powerpc/math-emu/fcmpu.c b/arch/powerpc/math-emu/fcmpu.c
index 53d9389..d4fb1ba 100644
--- a/arch/powerpc/math-emu/fcmpu.c
+++ b/arch/powerpc/math-emu/fcmpu.c
@@ -2,14 +2,16 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
 
 int
 fcmpu(u32 *ccr, int crfD, void *frA, void *frB)
 {
 	FP_DECL_D(A);
 	FP_DECL_D(B);
+	FP_DECL_EX;
 	int code[4] = { (1 << 3), (1 << 1), (1 << 2), (1 << 0) };
 	long cmp;
 
@@ -17,8 +19,8 @@
 	printk("%s: %p (%08x) %d %p %p\n", __func__, ccr, *ccr, crfD, frA, frB);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
diff --git a/arch/powerpc/math-emu/fctiw.c b/arch/powerpc/math-emu/fctiw.c
index fcd7a95..f694440 100644
--- a/arch/powerpc/math-emu/fctiw.c
+++ b/arch/powerpc/math-emu/fctiw.c
@@ -2,16 +2,18 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
 
 int
 fctiw(u32 *frD, void *frB)
 {
 	FP_DECL_D(B);
+	FP_DECL_EX;
 	unsigned int r;
 
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(B, frB);
 	FP_TO_INT_D(r, B, 32, 1);
 	frD[1] = r;
 
diff --git a/arch/powerpc/math-emu/fctiwz.c b/arch/powerpc/math-emu/fctiwz.c
index 1514d59..71e782f 100644
--- a/arch/powerpc/math-emu/fctiwz.c
+++ b/arch/powerpc/math-emu/fctiwz.c
@@ -2,13 +2,15 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
 
 int
 fctiwz(u32 *frD, void *frB)
 {
 	FP_DECL_D(B);
+	FP_DECL_EX;
 	u32 fpscr;
 	unsigned int r;
 
@@ -16,7 +18,7 @@
 	__FPU_FPSCR &= ~(3);
 	__FPU_FPSCR |= FP_RND_ZERO;
 
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(B, frB);
 	FP_TO_INT_D(r, B, 32, 1);
 	frD[1] = r;
 
diff --git a/arch/powerpc/math-emu/fdiv.c b/arch/powerpc/math-emu/fdiv.c
index 18a20fe..2db1509 100644
--- a/arch/powerpc/math-emu/fdiv.c
+++ b/arch/powerpc/math-emu/fdiv.c
@@ -2,8 +2,9 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
 
 int
 fdiv(void *frD, void *frA, void *frB)
@@ -11,14 +12,15 @@
 	FP_DECL_D(A);
 	FP_DECL_D(B);
 	FP_DECL_D(R);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
@@ -49,5 +51,7 @@
 	printk("D: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_D(frD, R));
+	__FP_PACK_D(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fdivs.c b/arch/powerpc/math-emu/fdivs.c
index 24feed6..797f6a9 100644
--- a/arch/powerpc/math-emu/fdivs.c
+++ b/arch/powerpc/math-emu/fdivs.c
@@ -2,9 +2,10 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
-#include "single.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
 
 int
 fdivs(void *frD, void *frA, void *frB)
@@ -12,14 +13,15 @@
 	FP_DECL_D(A);
 	FP_DECL_D(B);
 	FP_DECL_D(R);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
@@ -51,5 +53,7 @@
 	printk("D: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_DS(frD, R));
+	__FP_PACK_DS(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fmadd.c b/arch/powerpc/math-emu/fmadd.c
index dedb465..925313a 100644
--- a/arch/powerpc/math-emu/fmadd.c
+++ b/arch/powerpc/math-emu/fmadd.c
@@ -2,8 +2,9 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
 
 int
 fmadd(void *frD, void *frA, void *frB, void *frC)
@@ -13,15 +14,16 @@
 	FP_DECL_D(B);
 	FP_DECL_D(C);
 	FP_DECL_D(T);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
-	__FP_UNPACK_D(C, frC);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
+	FP_UNPACK_DP(C, frC);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
@@ -44,5 +46,7 @@
 	printk("D: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_D(frD, R));
+	__FP_PACK_D(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fmadds.c b/arch/powerpc/math-emu/fmadds.c
index 6bbb56d..aea80ef 100644
--- a/arch/powerpc/math-emu/fmadds.c
+++ b/arch/powerpc/math-emu/fmadds.c
@@ -2,9 +2,10 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
-#include "single.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
 
 int
 fmadds(void *frD, void *frA, void *frB, void *frC)
@@ -14,15 +15,16 @@
 	FP_DECL_D(B);
 	FP_DECL_D(C);
 	FP_DECL_D(T);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
-	__FP_UNPACK_D(C, frC);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
+	FP_UNPACK_DP(C, frC);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
@@ -45,5 +47,7 @@
 	printk("D: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_DS(frD, R));
+	__FP_PACK_DS(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fmsub.c b/arch/powerpc/math-emu/fmsub.c
index f311e2c..a644d52 100644
--- a/arch/powerpc/math-emu/fmsub.c
+++ b/arch/powerpc/math-emu/fmsub.c
@@ -2,8 +2,9 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
 
 int
 fmsub(void *frD, void *frA, void *frB, void *frC)
@@ -13,15 +14,16 @@
 	FP_DECL_D(B);
 	FP_DECL_D(C);
 	FP_DECL_D(T);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
-	__FP_UNPACK_D(C, frC);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
+	FP_UNPACK_DP(C, frC);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
@@ -47,5 +49,7 @@
 	printk("D: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_D(frD, R));
+	__FP_PACK_D(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fmsubs.c b/arch/powerpc/math-emu/fmsubs.c
index 81a716d..2fdeeb9 100644
--- a/arch/powerpc/math-emu/fmsubs.c
+++ b/arch/powerpc/math-emu/fmsubs.c
@@ -2,9 +2,10 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
-#include "single.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
 
 int
 fmsubs(void *frD, void *frA, void *frB, void *frC)
@@ -14,15 +15,16 @@
 	FP_DECL_D(B);
 	FP_DECL_D(C);
 	FP_DECL_D(T);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
-	__FP_UNPACK_D(C, frC);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
+	FP_UNPACK_DP(C, frC);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
@@ -48,5 +50,7 @@
 	printk("D: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_DS(frD, R));
+	__FP_PACK_DS(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fmul.c b/arch/powerpc/math-emu/fmul.c
index 2f3d327..391fd17 100644
--- a/arch/powerpc/math-emu/fmul.c
+++ b/arch/powerpc/math-emu/fmul.c
@@ -2,8 +2,9 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
 
 int
 fmul(void *frD, void *frA, void *frB)
@@ -11,14 +12,15 @@
 	FP_DECL_D(A);
 	FP_DECL_D(B);
 	FP_DECL_D(R);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld) [%08lx.%08lx %lx]\n",
@@ -38,5 +40,7 @@
 	       R_s, R_f1, R_f0, R_e, R_c, R_f1, R_f0, R_e + 1023);
 #endif
 
-	return (ret | __FP_PACK_D(frD, R));
+	__FP_PACK_D(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fmuls.c b/arch/powerpc/math-emu/fmuls.c
index 962b588..2d3ec5f 100644
--- a/arch/powerpc/math-emu/fmuls.c
+++ b/arch/powerpc/math-emu/fmuls.c
@@ -2,9 +2,10 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
-#include "single.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
 
 int
 fmuls(void *frD, void *frA, void *frB)
@@ -12,14 +13,15 @@
 	FP_DECL_D(A);
 	FP_DECL_D(B);
 	FP_DECL_D(R);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld) [%08lx.%08lx %lx]\n",
@@ -39,5 +41,7 @@
 	       R_s, R_f1, R_f0, R_e, R_c, R_f1, R_f0, R_e + 1023);
 #endif
 
-	return (ret | __FP_PACK_DS(frD, R));
+	__FP_PACK_DS(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fnmadd.c b/arch/powerpc/math-emu/fnmadd.c
index 8cf7827..2497b86 100644
--- a/arch/powerpc/math-emu/fnmadd.c
+++ b/arch/powerpc/math-emu/fnmadd.c
@@ -2,8 +2,9 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
 
 int
 fnmadd(void *frD, void *frA, void *frB, void *frC)
@@ -13,15 +14,16 @@
 	FP_DECL_D(B);
 	FP_DECL_D(C);
 	FP_DECL_D(T);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
-	__FP_UNPACK_D(C, frC);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
+	FP_UNPACK_DP(C, frC);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
@@ -47,5 +49,7 @@
 	printk("D: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_D(frD, R));
+	__FP_PACK_D(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fnmadds.c b/arch/powerpc/math-emu/fnmadds.c
index f1c4f0f..ee9d71e 100644
--- a/arch/powerpc/math-emu/fnmadds.c
+++ b/arch/powerpc/math-emu/fnmadds.c
@@ -2,9 +2,10 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
-#include "single.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
 
 int
 fnmadds(void *frD, void *frA, void *frB, void *frC)
@@ -14,15 +15,16 @@
 	FP_DECL_D(B);
 	FP_DECL_D(C);
 	FP_DECL_D(T);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
-	__FP_UNPACK_D(C, frC);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
+	FP_UNPACK_DP(C, frC);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
@@ -48,5 +50,7 @@
 	printk("D: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_DS(frD, R));
+	__FP_PACK_DS(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fnmsub.c b/arch/powerpc/math-emu/fnmsub.c
index 98944e6..3885a77 100644
--- a/arch/powerpc/math-emu/fnmsub.c
+++ b/arch/powerpc/math-emu/fnmsub.c
@@ -2,8 +2,9 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
 
 int
 fnmsub(void *frD, void *frA, void *frB, void *frC)
@@ -13,15 +14,16 @@
 	FP_DECL_D(B);
 	FP_DECL_D(C);
 	FP_DECL_D(T);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
-	__FP_UNPACK_D(C, frC);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
+	FP_UNPACK_DP(C, frC);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
@@ -50,5 +52,7 @@
 	printk("D: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_D(frD, R));
+	__FP_PACK_D(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fnmsubs.c b/arch/powerpc/math-emu/fnmsubs.c
index b20f4eb..f835dfe 100644
--- a/arch/powerpc/math-emu/fnmsubs.c
+++ b/arch/powerpc/math-emu/fnmsubs.c
@@ -2,9 +2,10 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
-#include "single.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
 
 int
 fnmsubs(void *frD, void *frA, void *frB, void *frC)
@@ -14,15 +15,16 @@
 	FP_DECL_D(B);
 	FP_DECL_D(C);
 	FP_DECL_D(T);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
-	__FP_UNPACK_D(C, frC);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
+	FP_UNPACK_DP(C, frC);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
@@ -51,5 +53,7 @@
 	printk("D: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_DS(frD, R));
+	__FP_PACK_DS(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/frsp.c b/arch/powerpc/math-emu/frsp.c
index 724ccbc..ddcc146 100644
--- a/arch/powerpc/math-emu/frsp.c
+++ b/arch/powerpc/math-emu/frsp.c
@@ -2,24 +2,28 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
-#include "single.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
 
 int
 frsp(void *frD, void *frB)
 {
 	FP_DECL_D(B);
+	FP_DECL_EX;
 
 #ifdef DEBUG
 	printk("%s: D %p, B %p\n", __func__, frD, frB);
 #endif
 
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(B, frB);
 
 #ifdef DEBUG
 	printk("B: %ld %lu %lu %ld (%ld)\n", B_s, B_f1, B_f0, B_e, B_c);
 #endif
 
-	return __FP_PACK_DS(frD, B);
+	__FP_PACK_DS(frD, B);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fsel.c b/arch/powerpc/math-emu/fsel.c
index ecb5f28..1b0c144 100644
--- a/arch/powerpc/math-emu/fsel.c
+++ b/arch/powerpc/math-emu/fsel.c
@@ -2,19 +2,21 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
 
 int
 fsel(u32 *frD, void *frA, u32 *frB, u32 *frC)
 {
 	FP_DECL_D(A);
+	FP_DECL_EX;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
 #endif
 
-	__FP_UNPACK_D(A, frA);
+	FP_UNPACK_DP(A, frA);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
diff --git a/arch/powerpc/math-emu/fsqrt.c b/arch/powerpc/math-emu/fsqrt.c
index 38ec2b7..3e90072 100644
--- a/arch/powerpc/math-emu/fsqrt.c
+++ b/arch/powerpc/math-emu/fsqrt.c
@@ -2,21 +2,23 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
 
 int
 fsqrt(void *frD, void *frB)
 {
 	FP_DECL_D(B);
 	FP_DECL_D(R);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frB);
 #endif
 
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(B, frB);
 
 #ifdef DEBUG
 	printk("B: %ld %lu %lu %ld (%ld)\n", B_s, B_f1, B_f0, B_e, B_c);
@@ -33,5 +35,7 @@
 	printk("R: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_D(frD, R));
+	__FP_PACK_D(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fsqrts.c b/arch/powerpc/math-emu/fsqrts.c
index 335263e..2843be9 100644
--- a/arch/powerpc/math-emu/fsqrts.c
+++ b/arch/powerpc/math-emu/fsqrts.c
@@ -2,22 +2,24 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
-#include "single.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
 
 int
 fsqrts(void *frD, void *frB)
 {
 	FP_DECL_D(B);
 	FP_DECL_D(R);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frB);
 #endif
 
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(B, frB);
 
 #ifdef DEBUG
 	printk("B: %ld %lu %lu %ld (%ld)\n", B_s, B_f1, B_f0, B_e, B_c);
@@ -34,5 +36,7 @@
 	printk("R: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_DS(frD, R));
+	__FP_PACK_DS(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fsub.c b/arch/powerpc/math-emu/fsub.c
index 208d20f..78b0944 100644
--- a/arch/powerpc/math-emu/fsub.c
+++ b/arch/powerpc/math-emu/fsub.c
@@ -2,8 +2,9 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
 
 int
 fsub(void *frD, void *frA, void *frB)
@@ -11,14 +12,15 @@
 	FP_DECL_D(A);
 	FP_DECL_D(B);
 	FP_DECL_D(R);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
@@ -37,5 +39,7 @@
 	printk("D: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_D(frD, R));
+	__FP_PACK_D(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fsubs.c b/arch/powerpc/math-emu/fsubs.c
index 0e61b80..d3bf908 100644
--- a/arch/powerpc/math-emu/fsubs.c
+++ b/arch/powerpc/math-emu/fsubs.c
@@ -2,9 +2,10 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
-#include "single.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
 
 int
 fsubs(void *frD, void *frA, void *frB)
@@ -12,14 +13,15 @@
 	FP_DECL_D(A);
 	FP_DECL_D(B);
 	FP_DECL_D(R);
+	FP_DECL_EX;
 	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
 #endif
 
-	__FP_UNPACK_D(A, frA);
-	__FP_UNPACK_D(B, frB);
+	FP_UNPACK_DP(A, frA);
+	FP_UNPACK_DP(B, frB);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
@@ -38,5 +40,7 @@
 	printk("D: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return (ret | __FP_PACK_DS(frD, R));
+	__FP_PACK_DS(frD, R);
+
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/lfd.c b/arch/powerpc/math-emu/lfd.c
index 6ec90b5..79ac76d 100644
--- a/arch/powerpc/math-emu/lfd.c
+++ b/arch/powerpc/math-emu/lfd.c
@@ -2,8 +2,8 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "sfp-machine.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/double.h>
 
 int
 lfd(void *frD, void *ea)
diff --git a/arch/powerpc/math-emu/lfs.c b/arch/powerpc/math-emu/lfs.c
index 6f18ebe..434ed27 100644
--- a/arch/powerpc/math-emu/lfs.c
+++ b/arch/powerpc/math-emu/lfs.c
@@ -2,15 +2,17 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
-#include "single.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
 
 int
 lfs(void *frD, void *ea)
 {
 	FP_DECL_D(R);
 	FP_DECL_S(A);
+	FP_DECL_EX;
 	float f;
 
 #ifdef DEBUG
@@ -20,7 +22,7 @@
 	if (copy_from_user(&f, ea, sizeof(float)))
 		return -EFAULT;
 
-	__FP_UNPACK_S(A, &f);
+	FP_UNPACK_S(A, f);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %ld (%ld) [%08lx]\n", A_s, A_f, A_e, A_c,
@@ -33,5 +35,12 @@
 	printk("R: %ld %lu %lu %ld (%ld)\n", R_s, R_f1, R_f0, R_e, R_c);
 #endif
 
-	return __FP_PACK_D(frD, R);
+	if (R_c == FP_CLS_NAN) {
+		R_e = _FP_EXPMAX_D;
+		_FP_PACK_RAW_2_P(D, frD, R);
+	} else {
+		__FP_PACK_D(frD, R);
+	}
+
+	return 0;
 }
diff --git a/arch/powerpc/math-emu/math.c b/arch/powerpc/math-emu/math.c
index 29e545e..164d559 100644
--- a/arch/powerpc/math-emu/math.c
+++ b/arch/powerpc/math-emu/math.c
@@ -8,8 +8,8 @@
 #include <asm/uaccess.h>
 #include <asm/reg.h>
 
-#include "sfp-machine.h"
-#include "double.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/double.h>
 
 #define FLOATFUNC(x)	extern int x(void *, void *, void *, void *)
 
@@ -168,6 +168,8 @@
 			fpscr |= FPSCR_ZX;
 		if (eflag & EFLAG_INEXACT)
 			fpscr |= FPSCR_XX;
+		if (eflag & EFLAG_INVALID)
+			fpscr |= FPSCR_VX;
 		if (eflag & EFLAG_VXSNAN)
 			fpscr |= FPSCR_VXSNAN;
 		if (eflag & EFLAG_VXISI)
@@ -188,7 +190,7 @@
 			fpscr |= FPSCR_VXCVI;
 	}
 
-	fpscr &= ~(FPSCR_VX);
+//	fpscr &= ~(FPSCR_VX);
 	if (fpscr & (FPSCR_VXSNAN | FPSCR_VXISI | FPSCR_VXIDI |
 		     FPSCR_VXZDZ | FPSCR_VXIMZ | FPSCR_VXVC |
 		     FPSCR_VXSOFT | FPSCR_VXSQRT | FPSCR_VXCVI))
diff --git a/arch/powerpc/math-emu/mcrfs.c b/arch/powerpc/math-emu/mcrfs.c
index 41ba247..e948d57 100644
--- a/arch/powerpc/math-emu/mcrfs.c
+++ b/arch/powerpc/math-emu/mcrfs.c
@@ -2,7 +2,8 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
 
 int
 mcrfs(u32 *ccr, u32 crfD, u32 crfS)
diff --git a/arch/powerpc/math-emu/mffs.c b/arch/powerpc/math-emu/mffs.c
index b0e2106..5526cf9 100644
--- a/arch/powerpc/math-emu/mffs.c
+++ b/arch/powerpc/math-emu/mffs.c
@@ -2,7 +2,8 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
 
 int
 mffs(u32 *frD)
diff --git a/arch/powerpc/math-emu/mtfsb0.c b/arch/powerpc/math-emu/mtfsb0.c
index d306235..bc98558 100644
--- a/arch/powerpc/math-emu/mtfsb0.c
+++ b/arch/powerpc/math-emu/mtfsb0.c
@@ -2,7 +2,8 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
 
 int
 mtfsb0(int crbD)
diff --git a/arch/powerpc/math-emu/mtfsb1.c b/arch/powerpc/math-emu/mtfsb1.c
index 2e94870..fe6ed5a 100644
--- a/arch/powerpc/math-emu/mtfsb1.c
+++ b/arch/powerpc/math-emu/mtfsb1.c
@@ -2,7 +2,8 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
 
 int
 mtfsb1(int crbD)
diff --git a/arch/powerpc/math-emu/mtfsf.c b/arch/powerpc/math-emu/mtfsf.c
index 48014d8..dbce92e 100644
--- a/arch/powerpc/math-emu/mtfsf.c
+++ b/arch/powerpc/math-emu/mtfsf.c
@@ -2,12 +2,14 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
 
 int
 mtfsf(unsigned int FM, u32 *frB)
 {
 	u32 mask;
+	u32 fpscr;
 
 	if (FM == 0)
 		return 0;
@@ -37,6 +39,22 @@
 	__FPU_FPSCR &= ~(mask);
 	__FPU_FPSCR |= (frB[1] & mask);
 
+	__FPU_FPSCR &= ~(FPSCR_VX);
+	if (__FPU_FPSCR & (FPSCR_VXSNAN | FPSCR_VXISI | FPSCR_VXIDI |
+		     FPSCR_VXZDZ | FPSCR_VXIMZ | FPSCR_VXVC |
+		     FPSCR_VXSOFT | FPSCR_VXSQRT | FPSCR_VXCVI))
+		__FPU_FPSCR |= FPSCR_VX;
+
+	fpscr = __FPU_FPSCR;
+	fpscr &= ~(FPSCR_FEX);
+	if (((fpscr & FPSCR_VX) && (fpscr & FPSCR_VE)) ||
+	    ((fpscr & FPSCR_OX) && (fpscr & FPSCR_OE)) ||
+	    ((fpscr & FPSCR_UX) && (fpscr & FPSCR_UE)) ||
+	    ((fpscr & FPSCR_ZX) && (fpscr & FPSCR_ZE)) ||
+	    ((fpscr & FPSCR_XX) && (fpscr & FPSCR_XE)))
+		fpscr |= FPSCR_FEX;
+	__FPU_FPSCR = fpscr;
+
 #ifdef DEBUG
 	printk("%s: %02x %p: %08lx\n", __func__, FM, frB, __FPU_FPSCR);
 #endif
diff --git a/arch/powerpc/math-emu/mtfsfi.c b/arch/powerpc/math-emu/mtfsfi.c
index 031e200..fd2acc2 100644
--- a/arch/powerpc/math-emu/mtfsfi.c
+++ b/arch/powerpc/math-emu/mtfsfi.c
@@ -2,7 +2,8 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
 
 int
 mtfsfi(unsigned int crfD, unsigned int IMM)
diff --git a/arch/powerpc/math-emu/op-1.h b/arch/powerpc/math-emu/op-1.h
deleted file mode 100644
index c92fa95..0000000
--- a/arch/powerpc/math-emu/op-1.h
+++ /dev/null
@@ -1,245 +0,0 @@
-/*
- * Basic one-word fraction declaration and manipulation.
- */
-
-#define _FP_FRAC_DECL_1(X)	_FP_W_TYPE X##_f
-#define _FP_FRAC_COPY_1(D,S)	(D##_f = S##_f)
-#define _FP_FRAC_SET_1(X,I)	(X##_f = I)
-#define _FP_FRAC_HIGH_1(X)	(X##_f)
-#define _FP_FRAC_LOW_1(X)	(X##_f)
-#define _FP_FRAC_WORD_1(X,w)	(X##_f)
-
-#define _FP_FRAC_ADDI_1(X,I)	(X##_f += I)
-#define _FP_FRAC_SLL_1(X,N)			\
-  do {						\
-    if (__builtin_constant_p(N) && (N) == 1)	\
-      X##_f += X##_f;				\
-    else					\
-      X##_f <<= (N);				\
-  } while (0)
-#define _FP_FRAC_SRL_1(X,N)	(X##_f >>= N)
-
-/* Right shift with sticky-lsb.  */
-#define _FP_FRAC_SRS_1(X,N,sz)	__FP_FRAC_SRS_1(X##_f, N, sz)
-
-#define __FP_FRAC_SRS_1(X,N,sz)						\
-   (X = (X >> (N) | (__builtin_constant_p(N) && (N) == 1		\
-		     ? X & 1 : (X << (_FP_W_TYPE_SIZE - (N))) != 0)))
-
-#define _FP_FRAC_ADD_1(R,X,Y)	(R##_f = X##_f + Y##_f)
-#define _FP_FRAC_SUB_1(R,X,Y)	(R##_f = X##_f - Y##_f)
-#define _FP_FRAC_CLZ_1(z, X)	__FP_CLZ(z, X##_f)
-
-/* Predicates */
-#define _FP_FRAC_NEGP_1(X)	((_FP_WS_TYPE)X##_f < 0)
-#define _FP_FRAC_ZEROP_1(X)	(X##_f == 0)
-#define _FP_FRAC_OVERP_1(fs,X)	(X##_f & _FP_OVERFLOW_##fs)
-#define _FP_FRAC_EQ_1(X, Y)	(X##_f == Y##_f)
-#define _FP_FRAC_GE_1(X, Y)	(X##_f >= Y##_f)
-#define _FP_FRAC_GT_1(X, Y)	(X##_f > Y##_f)
-
-#define _FP_ZEROFRAC_1		0
-#define _FP_MINFRAC_1		1
-
-/*
- * Unpack the raw bits of a native fp value.  Do not classify or
- * normalize the data.
- */
-
-#define _FP_UNPACK_RAW_1(fs, X, val)				\
-  do {								\
-    union _FP_UNION_##fs _flo; _flo.flt = (val);		\
-								\
-    X##_f = _flo.bits.frac;					\
-    X##_e = _flo.bits.exp;					\
-    X##_s = _flo.bits.sign;					\
-  } while (0)
-
-
-/*
- * Repack the raw bits of a native fp value.
- */
-
-#define _FP_PACK_RAW_1(fs, val, X)				\
-  do {								\
-    union _FP_UNION_##fs _flo;					\
-								\
-    _flo.bits.frac = X##_f;					\
-    _flo.bits.exp  = X##_e;					\
-    _flo.bits.sign = X##_s;					\
-								\
-    (val) = _flo.flt;						\
-  } while (0)
-
-
-/*
- * Multiplication algorithms:
- */
-
-/* Basic.  Assuming the host word size is >= 2*FRACBITS, we can do the
-   multiplication immediately.  */
-
-#define _FP_MUL_MEAT_1_imm(fs, R, X, Y)					\
-  do {									\
-    R##_f = X##_f * Y##_f;						\
-    /* Normalize since we know where the msb of the multiplicands	\
-       were (bit B), we know that the msb of the of the product is	\
-       at either 2B or 2B-1.  */					\
-    _FP_FRAC_SRS_1(R, _FP_WFRACBITS_##fs-1, 2*_FP_WFRACBITS_##fs);	\
-  } while (0)
-
-/* Given a 1W * 1W => 2W primitive, do the extended multiplication.  */
-
-#define _FP_MUL_MEAT_1_wide(fs, R, X, Y, doit)				\
-  do {									\
-    _FP_W_TYPE _Z_f0, _Z_f1;						\
-    doit(_Z_f1, _Z_f0, X##_f, Y##_f);					\
-    /* Normalize since we know where the msb of the multiplicands	\
-       were (bit B), we know that the msb of the of the product is	\
-       at either 2B or 2B-1.  */					\
-    _FP_FRAC_SRS_2(_Z, _FP_WFRACBITS_##fs-1, 2*_FP_WFRACBITS_##fs);	\
-    R##_f = _Z_f0;							\
-  } while (0)
-
-/* Finally, a simple widening multiply algorithm.  What fun!  */
-
-#define _FP_MUL_MEAT_1_hard(fs, R, X, Y)				\
-  do {									\
-    _FP_W_TYPE _xh, _xl, _yh, _yl, _z_f0, _z_f1, _a_f0, _a_f1;		\
-									\
-    /* split the words in half */					\
-    _xh = X##_f >> (_FP_W_TYPE_SIZE/2);					\
-    _xl = X##_f & (((_FP_W_TYPE)1 << (_FP_W_TYPE_SIZE/2)) - 1);		\
-    _yh = Y##_f >> (_FP_W_TYPE_SIZE/2);					\
-    _yl = Y##_f & (((_FP_W_TYPE)1 << (_FP_W_TYPE_SIZE/2)) - 1);		\
-									\
-    /* multiply the pieces */						\
-    _z_f0 = _xl * _yl;							\
-    _a_f0 = _xh * _yl;							\
-    _a_f1 = _xl * _yh;							\
-    _z_f1 = _xh * _yh;							\
-									\
-    /* reassemble into two full words */				\
-    if ((_a_f0 += _a_f1) < _a_f1)					\
-      _z_f1 += (_FP_W_TYPE)1 << (_FP_W_TYPE_SIZE/2);			\
-    _a_f1 = _a_f0 >> (_FP_W_TYPE_SIZE/2);				\
-    _a_f0 = _a_f0 << (_FP_W_TYPE_SIZE/2);				\
-    _FP_FRAC_ADD_2(_z, _z, _a);						\
-									\
-    /* normalize */							\
-    _FP_FRAC_SRS_2(_z, _FP_WFRACBITS_##fs - 1, 2*_FP_WFRACBITS_##fs);	\
-    R##_f = _z_f0;							\
-  } while (0)
-
-
-/*
- * Division algorithms:
- */
-
-/* Basic.  Assuming the host word size is >= 2*FRACBITS, we can do the
-   division immediately.  Give this macro either _FP_DIV_HELP_imm for
-   C primitives or _FP_DIV_HELP_ldiv for the ISO function.  Which you
-   choose will depend on what the compiler does with divrem4.  */
-
-#define _FP_DIV_MEAT_1_imm(fs, R, X, Y, doit)		\
-  do {							\
-    _FP_W_TYPE _q, _r;					\
-    X##_f <<= (X##_f < Y##_f				\
-	       ? R##_e--, _FP_WFRACBITS_##fs		\
-	       : _FP_WFRACBITS_##fs - 1);		\
-    doit(_q, _r, X##_f, Y##_f);				\
-    R##_f = _q | (_r != 0);				\
-  } while (0)
-
-/* GCC's longlong.h defines a 2W / 1W => (1W,1W) primitive udiv_qrnnd
-   that may be useful in this situation.  This first is for a primitive
-   that requires normalization, the second for one that does not.  Look
-   for UDIV_NEEDS_NORMALIZATION to tell which your machine needs.  */
-
-#define _FP_DIV_MEAT_1_udiv_norm(fs, R, X, Y)				\
-  do {									\
-    _FP_W_TYPE _nh, _nl, _q, _r;					\
-									\
-    /* Normalize Y -- i.e. make the most significant bit set.  */	\
-    Y##_f <<= _FP_WFRACXBITS_##fs - 1;					\
-									\
-    /* Shift X op correspondingly high, that is, up one full word.  */	\
-    if (X##_f <= Y##_f)							\
-      {									\
-	_nl = 0;							\
-	_nh = X##_f;							\
-      }									\
-    else								\
-      {									\
-	R##_e++;							\
-	_nl = X##_f << (_FP_W_TYPE_SIZE-1);				\
-	_nh = X##_f >> 1;						\
-      }									\
-    									\
-    udiv_qrnnd(_q, _r, _nh, _nl, Y##_f);				\
-    R##_f = _q | (_r != 0);						\
-  } while (0)
-
-#define _FP_DIV_MEAT_1_udiv(fs, R, X, Y)		\
-  do {							\
-    _FP_W_TYPE _nh, _nl, _q, _r;			\
-    if (X##_f < Y##_f)					\
-      {							\
-	R##_e--;					\
-	_nl = X##_f << _FP_WFRACBITS_##fs;		\
-	_nh = X##_f >> _FP_WFRACXBITS_##fs;		\
-      }							\
-    else						\
-      {							\
-	_nl = X##_f << (_FP_WFRACBITS_##fs - 1);	\
-	_nh = X##_f >> (_FP_WFRACXBITS_##fs + 1);	\
-      }							\
-    udiv_qrnnd(_q, _r, _nh, _nl, Y##_f);		\
-    R##_f = _q | (_r != 0);				\
-  } while (0)
-
-
-/*
- * Square root algorithms:
- * We have just one right now, maybe Newton approximation
- * should be added for those machines where division is fast.
- */
-
-#define _FP_SQRT_MEAT_1(R, S, T, X, q)			\
-  do {							\
-    while (q)						\
-      {							\
-        T##_f = S##_f + q;				\
-        if (T##_f <= X##_f)				\
-          {						\
-            S##_f = T##_f + q;				\
-            X##_f -= T##_f;				\
-            R##_f += q;					\
-          }						\
-        _FP_FRAC_SLL_1(X, 1);				\
-        q >>= 1;					\
-      }							\
-  } while (0)
-
-/*
- * Assembly/disassembly for converting to/from integral types.
- * No shifting or overflow handled here.
- */
-
-#define _FP_FRAC_ASSEMBLE_1(r, X, rsize)	(r = X##_f)
-#define _FP_FRAC_DISASSEMBLE_1(X, r, rsize)	(X##_f = r)
-
-
-/*
- * Convert FP values between word sizes
- */
-
-#define _FP_FRAC_CONV_1_1(dfs, sfs, D, S)				\
-  do {									\
-    D##_f = S##_f;							\
-    if (_FP_WFRACBITS_##sfs > _FP_WFRACBITS_##dfs)			\
-      _FP_FRAC_SRS_1(D, (_FP_WFRACBITS_##sfs-_FP_WFRACBITS_##dfs),	\
-		     _FP_WFRACBITS_##sfs);				\
-    else								\
-      D##_f <<= _FP_WFRACBITS_##dfs - _FP_WFRACBITS_##sfs;		\
-  } while (0)
diff --git a/arch/powerpc/math-emu/op-2.h b/arch/powerpc/math-emu/op-2.h
deleted file mode 100644
index 7d6f17c..0000000
--- a/arch/powerpc/math-emu/op-2.h
+++ /dev/null
@@ -1,434 +0,0 @@
-/*
- * Basic two-word fraction declaration and manipulation.
- */
-
-#define _FP_FRAC_DECL_2(X)	_FP_W_TYPE X##_f0, X##_f1
-#define _FP_FRAC_COPY_2(D,S)	(D##_f0 = S##_f0, D##_f1 = S##_f1)
-#define _FP_FRAC_SET_2(X,I)	__FP_FRAC_SET_2(X, I)
-#define _FP_FRAC_HIGH_2(X)	(X##_f1)
-#define _FP_FRAC_LOW_2(X)	(X##_f0)
-#define _FP_FRAC_WORD_2(X,w)	(X##_f##w)
-
-#define _FP_FRAC_SLL_2(X,N)						\
-  do {									\
-    if ((N) < _FP_W_TYPE_SIZE)						\
-      {									\
-        if (__builtin_constant_p(N) && (N) == 1) 			\
-          {								\
-            X##_f1 = X##_f1 + X##_f1 + (((_FP_WS_TYPE)(X##_f0)) < 0);	\
-            X##_f0 += X##_f0;						\
-          }								\
-        else								\
-          {								\
-	    X##_f1 = X##_f1 << (N) | X##_f0 >> (_FP_W_TYPE_SIZE - (N));	\
-	    X##_f0 <<= (N);						\
-	  }								\
-      }									\
-    else								\
-      {									\
-	X##_f1 = X##_f0 << ((N) - _FP_W_TYPE_SIZE);			\
-	X##_f0 = 0;							\
-      }									\
-  } while (0)
-
-#define _FP_FRAC_SRL_2(X,N)						\
-  do {									\
-    if ((N) < _FP_W_TYPE_SIZE)						\
-      {									\
-	X##_f0 = X##_f0 >> (N) | X##_f1 << (_FP_W_TYPE_SIZE - (N));	\
-	X##_f1 >>= (N);							\
-      }									\
-    else								\
-      {									\
-	X##_f0 = X##_f1 >> ((N) - _FP_W_TYPE_SIZE);			\
-	X##_f1 = 0;							\
-      }									\
-  } while (0)
-
-/* Right shift with sticky-lsb.  */
-#define _FP_FRAC_SRS_2(X,N,sz)						\
-  do {									\
-    if ((N) < _FP_W_TYPE_SIZE)						\
-      {									\
-	X##_f0 = (X##_f1 << (_FP_W_TYPE_SIZE - (N)) | X##_f0 >> (N) |	\
-		  (__builtin_constant_p(N) && (N) == 1			\
-		   ? X##_f0 & 1						\
-		   : (X##_f0 << (_FP_W_TYPE_SIZE - (N))) != 0));	\
-	X##_f1 >>= (N);							\
-      }									\
-    else								\
-      {									\
-	X##_f0 = (X##_f1 >> ((N) - _FP_W_TYPE_SIZE) |			\
-	          (((X##_f1 << (2 * _FP_W_TYPE_SIZE - (N))) |		\
-		   X##_f0) != 0));					\
-	X##_f1 = 0;							\
-      }									\
-  } while (0)
-
-#define _FP_FRAC_ADDI_2(X,I) \
-  __FP_FRAC_ADDI_2(X##_f1, X##_f0, I)
-
-#define _FP_FRAC_ADD_2(R,X,Y) \
-  __FP_FRAC_ADD_2(R##_f1, R##_f0, X##_f1, X##_f0, Y##_f1, Y##_f0)
-
-#define _FP_FRAC_SUB_2(R,X,Y) \
-  __FP_FRAC_SUB_2(R##_f1, R##_f0, X##_f1, X##_f0, Y##_f1, Y##_f0)
-
-#define _FP_FRAC_CLZ_2(R,X)	\
-  do {				\
-    if (X##_f1)			\
-      __FP_CLZ(R,X##_f1);	\
-    else 			\
-    {				\
-      __FP_CLZ(R,X##_f0);	\
-      R += _FP_W_TYPE_SIZE;	\
-    }				\
-  } while(0)
-
-/* Predicates */
-#define _FP_FRAC_NEGP_2(X)	((_FP_WS_TYPE)X##_f1 < 0)
-#define _FP_FRAC_ZEROP_2(X)	((X##_f1 | X##_f0) == 0)
-#define _FP_FRAC_OVERP_2(fs,X)	(X##_f1 & _FP_OVERFLOW_##fs)
-#define _FP_FRAC_EQ_2(X, Y)	(X##_f1 == Y##_f1 && X##_f0 == Y##_f0)
-#define _FP_FRAC_GT_2(X, Y)	\
-  ((X##_f1 > Y##_f1) || (X##_f1 == Y##_f1 && X##_f0 > Y##_f0))
-#define _FP_FRAC_GE_2(X, Y)	\
-  ((X##_f1 > Y##_f1) || (X##_f1 == Y##_f1 && X##_f0 >= Y##_f0))
-
-#define _FP_ZEROFRAC_2		0, 0
-#define _FP_MINFRAC_2		0, 1
-
-/*
- * Internals
- */
-
-#define __FP_FRAC_SET_2(X,I1,I0)	(X##_f0 = I0, X##_f1 = I1)
-
-#define __FP_CLZ_2(R, xh, xl)	\
-  do {				\
-    if (xh)			\
-      __FP_CLZ(R,xl);		\
-    else 			\
-    {				\
-      __FP_CLZ(R,xl);		\
-      R += _FP_W_TYPE_SIZE;	\
-    }				\
-  } while(0)
-
-#if 0
-
-#ifndef __FP_FRAC_ADDI_2
-#define __FP_FRAC_ADDI_2(xh, xl, i) \
-  (xh += ((xl += i) < i))
-#endif
-#ifndef __FP_FRAC_ADD_2
-#define __FP_FRAC_ADD_2(rh, rl, xh, xl, yh, yl) \
-  (rh = xh + yh + ((rl = xl + yl) < xl))
-#endif
-#ifndef __FP_FRAC_SUB_2
-#define __FP_FRAC_SUB_2(rh, rl, xh, xl, yh, yl) \
-  (rh = xh - yh - ((rl = xl - yl) > xl))
-#endif
-
-#else
-
-#undef __FP_FRAC_ADDI_2
-#define __FP_FRAC_ADDI_2(xh, xl, i)	add_ssaaaa(xh, xl, xh, xl, 0, i)
-#undef __FP_FRAC_ADD_2
-#define __FP_FRAC_ADD_2			add_ssaaaa
-#undef __FP_FRAC_SUB_2
-#define __FP_FRAC_SUB_2			sub_ddmmss
-
-#endif
-
-/*
- * Unpack the raw bits of a native fp value.  Do not classify or
- * normalize the data.
- */
-
-#define _FP_UNPACK_RAW_2(fs, X, val)			\
-  do {							\
-    union _FP_UNION_##fs _flo; _flo.flt = (val);	\
-							\
-    X##_f0 = _flo.bits.frac0;				\
-    X##_f1 = _flo.bits.frac1;				\
-    X##_e  = _flo.bits.exp;				\
-    X##_s  = _flo.bits.sign;				\
-  } while (0)
-
-
-/*
- * Repack the raw bits of a native fp value.
- */
-
-#define _FP_PACK_RAW_2(fs, val, X)			\
-  do {							\
-    union _FP_UNION_##fs _flo;				\
-							\
-    _flo.bits.frac0 = X##_f0;				\
-    _flo.bits.frac1 = X##_f1;				\
-    _flo.bits.exp   = X##_e;				\
-    _flo.bits.sign  = X##_s;				\
-							\
-    (val) = _flo.flt;					\
-  } while (0)
-
-
-/*
- * Multiplication algorithms:
- */
-
-/* Given a 1W * 1W => 2W primitive, do the extended multiplication.  */
-
-#define _FP_MUL_MEAT_2_wide(fs, R, X, Y, doit)				\
-  do {									\
-    _FP_FRAC_DECL_4(_z); _FP_FRAC_DECL_2(_b); _FP_FRAC_DECL_2(_c);	\
-									\
-    doit(_FP_FRAC_WORD_4(_z,1), _FP_FRAC_WORD_4(_z,0), X##_f0, Y##_f0); \
-    doit(_b_f1, _b_f0, X##_f0, Y##_f1);					\
-    doit(_c_f1, _c_f0, X##_f1, Y##_f0);					\
-    doit(_FP_FRAC_WORD_4(_z,3), _FP_FRAC_WORD_4(_z,2), X##_f1, Y##_f1); \
-									\
-    __FP_FRAC_ADD_4(_FP_FRAC_WORD_4(_z,3),_FP_FRAC_WORD_4(_z,2),	\
-		    _FP_FRAC_WORD_4(_z,1),_FP_FRAC_WORD_4(_z,0),	\
-		    0, _b_f1, _b_f0, 0,					\
-		    _FP_FRAC_WORD_4(_z,3),_FP_FRAC_WORD_4(_z,2),	\
-		    _FP_FRAC_WORD_4(_z,1),_FP_FRAC_WORD_4(_z,0));	\
-    __FP_FRAC_ADD_4(_FP_FRAC_WORD_4(_z,3),_FP_FRAC_WORD_4(_z,2),	\
-		    _FP_FRAC_WORD_4(_z,1),_FP_FRAC_WORD_4(_z,0),	\
-		    0, _c_f1, _c_f0, 0,					\
-		    _FP_FRAC_WORD_4(_z,3),_FP_FRAC_WORD_4(_z,2),	\
-		    _FP_FRAC_WORD_4(_z,1),_FP_FRAC_WORD_4(_z,0));	\
-									\
-    /* Normalize since we know where the msb of the multiplicands	\
-       were (bit B), we know that the msb of the of the product is	\
-       at either 2B or 2B-1.  */					\
-    _FP_FRAC_SRS_4(_z, _FP_WFRACBITS_##fs-1, 2*_FP_WFRACBITS_##fs);	\
-    R##_f0 = _FP_FRAC_WORD_4(_z,0);					\
-    R##_f1 = _FP_FRAC_WORD_4(_z,1);					\
-  } while (0)
-
-/* This next macro appears to be totally broken. Fortunately nowhere
- * seems to use it :-> The problem is that we define _z[4] but
- * then use it in _FP_FRAC_SRS_4, which will attempt to access
- * _z_f[n] which will cause an error. The fix probably involves
- * declaring it with _FP_FRAC_DECL_4, see previous macro. -- PMM 02/1998
- */
-#define _FP_MUL_MEAT_2_gmp(fs, R, X, Y)					\
-  do {									\
-    _FP_W_TYPE _x[2], _y[2], _z[4];					\
-    _x[0] = X##_f0; _x[1] = X##_f1;					\
-    _y[0] = Y##_f0; _y[1] = Y##_f1;					\
-									\
-    mpn_mul_n(_z, _x, _y, 2);						\
-									\
-    /* Normalize since we know where the msb of the multiplicands	\
-       were (bit B), we know that the msb of the of the product is	\
-       at either 2B or 2B-1.  */					\
-    _FP_FRAC_SRS_4(_z, _FP_WFRACBITS##_fs-1, 2*_FP_WFRACBITS_##fs);	\
-    R##_f0 = _z[0];							\
-    R##_f1 = _z[1];							\
-  } while (0)
-
-
-/*
- * Division algorithms:
- * This seems to be giving me difficulties -- PMM
- * Look, NetBSD seems to be able to comment algorithms. Can't you?
- * I've thrown printks at the problem.
- * This now appears to work, but I still don't really know why.
- * Also, I don't think the result is properly normalised...
- */
-
-#define _FP_DIV_MEAT_2_udiv_64(fs, R, X, Y)				\
-  do {									\
-    extern void _fp_udivmodti4(_FP_W_TYPE q[2], _FP_W_TYPE r[2],	\
-			       _FP_W_TYPE n1, _FP_W_TYPE n0,		\
-			       _FP_W_TYPE d1, _FP_W_TYPE d0);		\
-    _FP_W_TYPE _n_f3, _n_f2, _n_f1, _n_f0, _r_f1, _r_f0;		\
-    _FP_W_TYPE _q_f1, _q_f0, _m_f1, _m_f0;				\
-    _FP_W_TYPE _rmem[2], _qmem[2];					\
-    /* I think this check is to ensure that the result is normalised.   \
-     * Assuming X,Y normalised (ie in [1.0,2.0)) X/Y will be in         \
-     * [0.5,2.0). Furthermore, it will be less than 1.0 iff X < Y.      \
-     * In this case we tweak things. (this is based on comments in      \
-     * the NetBSD FPU emulation code. )                                 \
-     * We know X,Y are normalised because we ensure this as part of     \
-     * the unpacking process. -- PMM                                    \
-     */									\
-    if (_FP_FRAC_GT_2(X, Y))						\
-      {									\
-/*	R##_e++; */							\
-	_n_f3 = X##_f1 >> 1;						\
-	_n_f2 = X##_f1 << (_FP_W_TYPE_SIZE - 1) | X##_f0 >> 1;		\
-	_n_f1 = X##_f0 << (_FP_W_TYPE_SIZE - 1);			\
-	_n_f0 = 0;							\
-      }									\
-    else								\
-      {									\
-	R##_e--;							\
-	_n_f3 = X##_f1;							\
-	_n_f2 = X##_f0;							\
-	_n_f1 = _n_f0 = 0;						\
-      }									\
-									\
-    /* Normalize, i.e. make the most significant bit of the 		\
-       denominator set.  CHANGED: - 1 to nothing -- PMM */		\
-    _FP_FRAC_SLL_2(Y, _FP_WFRACXBITS_##fs /* -1 */);			\
-									\
-    /* Do the 256/128 bit division given the 128-bit _fp_udivmodtf4 	\
-       primitive snagged from libgcc2.c.  */				\
-									\
-    _fp_udivmodti4(_qmem, _rmem, _n_f3, _n_f2, 0, Y##_f1);		\
-    _q_f1 = _qmem[0];							\
-    umul_ppmm(_m_f1, _m_f0, _q_f1, Y##_f0);				\
-    _r_f1 = _rmem[0];							\
-    _r_f0 = _n_f1;							\
-    if (_FP_FRAC_GT_2(_m, _r))						\
-      {									\
-	_q_f1--;							\
-	_FP_FRAC_ADD_2(_r, _r, Y);					\
-	if (_FP_FRAC_GE_2(_r, Y) && _FP_FRAC_GT_2(_m, _r))		\
-	  {								\
-	    _q_f1--;							\
-	    _FP_FRAC_ADD_2(_r, _r, Y);					\
-	  }								\
-      }									\
-    _FP_FRAC_SUB_2(_r, _r, _m);						\
-									\
-    _fp_udivmodti4(_qmem, _rmem, _r_f1, _r_f0, 0, Y##_f1);		\
-    _q_f0 = _qmem[0];							\
-    umul_ppmm(_m_f1, _m_f0, _q_f0, Y##_f0);				\
-    _r_f1 = _rmem[0];							\
-    _r_f0 = _n_f0;							\
-    if (_FP_FRAC_GT_2(_m, _r))						\
-      {									\
-	_q_f0--;							\
-	_FP_FRAC_ADD_2(_r, _r, Y);					\
-	if (_FP_FRAC_GE_2(_r, Y) && _FP_FRAC_GT_2(_m, _r))		\
-	  {								\
-	    _q_f0--;							\
-	    _FP_FRAC_ADD_2(_r, _r, Y);					\
-	  }								\
-      }									\
-    _FP_FRAC_SUB_2(_r, _r, _m);						\
-									\
-    R##_f1 = _q_f1;							\
-    R##_f0 = _q_f0 | ((_r_f1 | _r_f0) != 0);				\
-    /* adjust so answer is normalized again. I'm not sure what the 	\
-     * final sz param should be. In practice it's never used since      \
-     * N is 1 which is always going to be < _FP_W_TYPE_SIZE...		\
-     */									\
-    /* _FP_FRAC_SRS_2(R,1,_FP_WFRACBITS_##fs);	*/			\
-  } while (0)
-
-
-#define _FP_DIV_MEAT_2_gmp(fs, R, X, Y)					\
-  do {									\
-    _FP_W_TYPE _x[4], _y[2], _z[4];					\
-    _y[0] = Y##_f0; _y[1] = Y##_f1;					\
-    _x[0] = _x[3] = 0;							\
-    if (_FP_FRAC_GT_2(X, Y))						\
-      {									\
-	R##_e++;							\
-	_x[1] = (X##_f0 << (_FP_WFRACBITS-1 - _FP_W_TYPE_SIZE) |	\
-		 X##_f1 >> (_FP_W_TYPE_SIZE -				\
-			    (_FP_WFRACBITS-1 - _FP_W_TYPE_SIZE)));	\
-	_x[2] = X##_f1 << (_FP_WFRACBITS-1 - _FP_W_TYPE_SIZE);		\
-      }									\
-    else								\
-      {									\
-	_x[1] = (X##_f0 << (_FP_WFRACBITS - _FP_W_TYPE_SIZE) |		\
-		 X##_f1 >> (_FP_W_TYPE_SIZE -				\
-			    (_FP_WFRACBITS - _FP_W_TYPE_SIZE)));	\
-	_x[2] = X##_f1 << (_FP_WFRACBITS - _FP_W_TYPE_SIZE);		\
-      }									\
-									\
-    (void) mpn_divrem (_z, 0, _x, 4, _y, 2);				\
-    R##_f1 = _z[1];							\
-    R##_f0 = _z[0] | ((_x[0] | _x[1]) != 0);				\
-  } while (0)
-
-
-/*
- * Square root algorithms:
- * We have just one right now, maybe Newton approximation
- * should be added for those machines where division is fast.
- */
-
-#define _FP_SQRT_MEAT_2(R, S, T, X, q)			\
-  do {							\
-    while (q)						\
-      {							\
-        T##_f1 = S##_f1 + q;				\
-        if (T##_f1 <= X##_f1)				\
-          {						\
-            S##_f1 = T##_f1 + q;			\
-            X##_f1 -= T##_f1;				\
-            R##_f1 += q;				\
-          }						\
-        _FP_FRAC_SLL_2(X, 1);				\
-        q >>= 1;					\
-      }							\
-    q = (_FP_W_TYPE)1 << (_FP_W_TYPE_SIZE - 1);		\
-    while (q)						\
-      {							\
-        T##_f0 = S##_f0 + q;				\
-        T##_f1 = S##_f1;				\
-        if (T##_f1 < X##_f1 || 				\
-            (T##_f1 == X##_f1 && T##_f0 < X##_f0))	\
-          {						\
-            S##_f0 = T##_f0 + q;			\
-            if (((_FP_WS_TYPE)T##_f0) < 0 &&		\
-                ((_FP_WS_TYPE)S##_f0) >= 0)		\
-              S##_f1++;					\
-            _FP_FRAC_SUB_2(X, X, T);			\
-            R##_f0 += q;				\
-          }						\
-        _FP_FRAC_SLL_2(X, 1);				\
-        q >>= 1;					\
-      }							\
-  } while (0)
-
-
-/*
- * Assembly/disassembly for converting to/from integral types.
- * No shifting or overflow handled here.
- */
-
-#define _FP_FRAC_ASSEMBLE_2(r, X, rsize)	\
-  do {						\
-    if (rsize <= _FP_W_TYPE_SIZE)		\
-      r = X##_f0;				\
-    else					\
-      {						\
-	r = X##_f1;				\
-	r <<= _FP_W_TYPE_SIZE;			\
-	r += X##_f0;				\
-      }						\
-  } while (0)
-
-#define _FP_FRAC_DISASSEMBLE_2(X, r, rsize)				\
-  do {									\
-    X##_f0 = r;								\
-    X##_f1 = (rsize <= _FP_W_TYPE_SIZE ? 0 : r >> _FP_W_TYPE_SIZE);	\
-  } while (0)
-
-/*
- * Convert FP values between word sizes
- */
-
-#define _FP_FRAC_CONV_1_2(dfs, sfs, D, S)				\
-  do {									\
-    _FP_FRAC_SRS_2(S, (_FP_WFRACBITS_##sfs - _FP_WFRACBITS_##dfs),	\
-		   _FP_WFRACBITS_##sfs);				\
-    D##_f = S##_f0;							\
-  } while (0)
-
-#define _FP_FRAC_CONV_2_1(dfs, sfs, D, S)				\
-  do {									\
-    D##_f0 = S##_f;							\
-    D##_f1 = 0;								\
-    _FP_FRAC_SLL_2(D, (_FP_WFRACBITS_##dfs - _FP_WFRACBITS_##sfs));	\
-  } while (0)
-
diff --git a/arch/powerpc/math-emu/op-4.h b/arch/powerpc/math-emu/op-4.h
deleted file mode 100644
index c9ae626..0000000
--- a/arch/powerpc/math-emu/op-4.h
+++ /dev/null
@@ -1,317 +0,0 @@
-/*
- * Basic four-word fraction declaration and manipulation.
- *
- * When adding quadword support for 32 bit machines, we need
- * to be a little careful as double multiply uses some of these
- * macros: (in op-2.h)
- * _FP_MUL_MEAT_2_wide() uses _FP_FRAC_DECL_4, _FP_FRAC_WORD_4,
- * _FP_FRAC_ADD_4, _FP_FRAC_SRS_4
- * _FP_MUL_MEAT_2_gmp() uses _FP_FRAC_SRS_4 (and should use
- * _FP_FRAC_DECL_4: it appears to be broken and is not used
- * anywhere anyway. )
- *
- * I've now fixed all the macros that were here from the sparc64 code.
- * [*none* of the shift macros were correct!] -- PMM 02/1998
- *
- * The only quadword stuff that remains to be coded is:
- * 1) the conversion to/from ints, which requires
- * that we check (in op-common.h) that the following do the right thing
- * for quadwords: _FP_TO_INT(Q,4,r,X,rsz,rsg), _FP_FROM_INT(Q,4,X,r,rs,rt)
- * 2) multiply, divide and sqrt, which require:
- * _FP_MUL_MEAT_4_*(R,X,Y), _FP_DIV_MEAT_4_*(R,X,Y), _FP_SQRT_MEAT_4(R,S,T,X,q),
- * This also needs _FP_MUL_MEAT_Q and _FP_DIV_MEAT_Q to be defined to
- * some suitable _FP_MUL_MEAT_4_* macros in sfp-machine.h.
- * [we're free to choose whatever FP_MUL_MEAT_4_* macros we need for
- * these; they are used nowhere else. ]
- */
-
-#define _FP_FRAC_DECL_4(X)	_FP_W_TYPE X##_f[4]
-#define _FP_FRAC_COPY_4(D,S)			\
-  (D##_f[0] = S##_f[0], D##_f[1] = S##_f[1],	\
-   D##_f[2] = S##_f[2], D##_f[3] = S##_f[3])
-/* The _FP_FRAC_SET_n(X,I) macro is intended for use with another
- * macro such as _FP_ZEROFRAC_n which returns n comma separated values.
- * The result is that we get an expansion of __FP_FRAC_SET_n(X,I0,I1,I2,I3)
- * which just assigns the In values to the array X##_f[].
- * This is why the number of parameters doesn't appear to match
- * at first glance...      -- PMM
- */
-#define _FP_FRAC_SET_4(X,I)	__FP_FRAC_SET_4(X, I)
-#define _FP_FRAC_HIGH_4(X)	(X##_f[3])
-#define _FP_FRAC_LOW_4(X)	(X##_f[0])
-#define _FP_FRAC_WORD_4(X,w)	(X##_f[w])
-
-#define _FP_FRAC_SLL_4(X,N)						\
-  do {									\
-    _FP_I_TYPE _up, _down, _skip, _i;					\
-    _skip = (N) / _FP_W_TYPE_SIZE;					\
-    _up = (N) % _FP_W_TYPE_SIZE;					\
-    _down = _FP_W_TYPE_SIZE - _up;					\
-    for (_i = 3; _i > _skip; --_i)					\
-      X##_f[_i] = X##_f[_i-_skip] << _up | X##_f[_i-_skip-1] >> _down;	\
-/* bugfixed: was X##_f[_i] <<= _up;  -- PMM 02/1998 */                  \
-    X##_f[_i] = X##_f[0] << _up; 	                                \
-    for (--_i; _i >= 0; --_i)						\
-      X##_f[_i] = 0;							\
-  } while (0)
-
-/* This one was broken too */
-#define _FP_FRAC_SRL_4(X,N)						\
-  do {									\
-    _FP_I_TYPE _up, _down, _skip, _i;					\
-    _skip = (N) / _FP_W_TYPE_SIZE;					\
-    _down = (N) % _FP_W_TYPE_SIZE;					\
-    _up = _FP_W_TYPE_SIZE - _down;					\
-    for (_i = 0; _i < 3-_skip; ++_i)					\
-      X##_f[_i] = X##_f[_i+_skip] >> _down | X##_f[_i+_skip+1] << _up;	\
-    X##_f[_i] = X##_f[3] >> _down;			         	\
-    for (++_i; _i < 4; ++_i)						\
-      X##_f[_i] = 0;							\
-  } while (0)
-
-
-/* Right shift with sticky-lsb.
- * What this actually means is that we do a standard right-shift,
- * but that if any of the bits that fall off the right hand side
- * were one then we always set the LSbit.
- */
-#define _FP_FRAC_SRS_4(X,N,size)					\
-  do {									\
-    _FP_I_TYPE _up, _down, _skip, _i;					\
-    _FP_W_TYPE _s;							\
-    _skip = (N) / _FP_W_TYPE_SIZE;					\
-    _down = (N) % _FP_W_TYPE_SIZE;					\
-    _up = _FP_W_TYPE_SIZE - _down;					\
-    for (_s = _i = 0; _i < _skip; ++_i)					\
-      _s |= X##_f[_i];							\
-    _s |= X##_f[_i] << _up;						\
-/* s is now != 0 if we want to set the LSbit */                         \
-    for (_i = 0; _i < 3-_skip; ++_i)					\
-      X##_f[_i] = X##_f[_i+_skip] >> _down | X##_f[_i+_skip+1] << _up;	\
-    X##_f[_i] = X##_f[3] >> _down;					\
-    for (++_i; _i < 4; ++_i)						\
-      X##_f[_i] = 0;							\
-    /* don't fix the LSB until the very end when we're sure f[0] is stable */ \
-    X##_f[0] |= (_s != 0);                                              \
-  } while (0)
-
-#define _FP_FRAC_ADD_4(R,X,Y)						\
-  __FP_FRAC_ADD_4(R##_f[3], R##_f[2], R##_f[1], R##_f[0],		\
-		  X##_f[3], X##_f[2], X##_f[1], X##_f[0],		\
-		  Y##_f[3], Y##_f[2], Y##_f[1], Y##_f[0])
-
-#define _FP_FRAC_SUB_4(R,X,Y)                                           \
-  __FP_FRAC_SUB_4(R##_f[3], R##_f[2], R##_f[1], R##_f[0],		\
-		  X##_f[3], X##_f[2], X##_f[1], X##_f[0],		\
-		  Y##_f[3], Y##_f[2], Y##_f[1], Y##_f[0])
-
-#define _FP_FRAC_ADDI_4(X,I)                                            \
-  __FP_FRAC_ADDI_4(X##_f[3], X##_f[2], X##_f[1], X##_f[0], I)
-
-#define _FP_ZEROFRAC_4  0,0,0,0
-#define _FP_MINFRAC_4   0,0,0,1
-
-#define _FP_FRAC_ZEROP_4(X)     ((X##_f[0] | X##_f[1] | X##_f[2] | X##_f[3]) == 0)
-#define _FP_FRAC_NEGP_4(X)      ((_FP_WS_TYPE)X##_f[3] < 0)
-#define _FP_FRAC_OVERP_4(fs,X)  (X##_f[0] & _FP_OVERFLOW_##fs)
-
-#define _FP_FRAC_EQ_4(X,Y)                              \
- (X##_f[0] == Y##_f[0] && X##_f[1] == Y##_f[1]          \
-  && X##_f[2] == Y##_f[2] && X##_f[3] == Y##_f[3])
-
-#define _FP_FRAC_GT_4(X,Y)                              \
- (X##_f[3] > Y##_f[3] ||                                \
-  (X##_f[3] == Y##_f[3] && (X##_f[2] > Y##_f[2] ||      \
-   (X##_f[2] == Y##_f[2] && (X##_f[1] > Y##_f[1] ||     \
-    (X##_f[1] == Y##_f[1] && X##_f[0] > Y##_f[0])       \
-   ))                                                   \
-  ))                                                    \
- )
-
-#define _FP_FRAC_GE_4(X,Y)                              \
- (X##_f[3] > Y##_f[3] ||                                \
-  (X##_f[3] == Y##_f[3] && (X##_f[2] > Y##_f[2] ||      \
-   (X##_f[2] == Y##_f[2] && (X##_f[1] > Y##_f[1] ||     \
-    (X##_f[1] == Y##_f[1] && X##_f[0] >= Y##_f[0])      \
-   ))                                                   \
-  ))                                                    \
- )
-
-
-#define _FP_FRAC_CLZ_4(R,X)             \
-  do {                                  \
-    if (X##_f[3])                       \
-    {                                   \
-        __FP_CLZ(R,X##_f[3]);           \
-    }                                   \
-    else if (X##_f[2])                  \
-    {                                   \
-        __FP_CLZ(R,X##_f[2]);           \
-        R += _FP_W_TYPE_SIZE;           \
-    }                                   \
-    else if (X##_f[1])                  \
-    {                                   \
-        __FP_CLZ(R,X##_f[2]);           \
-        R += _FP_W_TYPE_SIZE*2;         \
-    }                                   \
-    else                                \
-    {                                   \
-        __FP_CLZ(R,X##_f[0]);           \
-        R += _FP_W_TYPE_SIZE*3;         \
-    }                                   \
-  } while(0)
-
-
-#define _FP_UNPACK_RAW_4(fs, X, val)                            \
-  do {                                                          \
-    union _FP_UNION_##fs _flo; _flo.flt = (val);        	\
-    X##_f[0] = _flo.bits.frac0;                                 \
-    X##_f[1] = _flo.bits.frac1;                                 \
-    X##_f[2] = _flo.bits.frac2;                                 \
-    X##_f[3] = _flo.bits.frac3;                                 \
-    X##_e  = _flo.bits.exp;                                     \
-    X##_s  = _flo.bits.sign;                                    \
-  } while (0)
-
-#define _FP_PACK_RAW_4(fs, val, X)                              \
-  do {                                                          \
-    union _FP_UNION_##fs _flo;					\
-    _flo.bits.frac0 = X##_f[0];                                 \
-    _flo.bits.frac1 = X##_f[1];                                 \
-    _flo.bits.frac2 = X##_f[2];                                 \
-    _flo.bits.frac3 = X##_f[3];                                 \
-    _flo.bits.exp   = X##_e;                                    \
-    _flo.bits.sign  = X##_s;                                    \
-    (val) = _flo.flt;                                   	\
-  } while (0)
-
-
-/*
- * Internals
- */
-
-#define __FP_FRAC_SET_4(X,I3,I2,I1,I0)					\
-  (X##_f[3] = I3, X##_f[2] = I2, X##_f[1] = I1, X##_f[0] = I0)
-
-#ifndef __FP_FRAC_ADD_4
-#define __FP_FRAC_ADD_4(r3,r2,r1,r0,x3,x2,x1,x0,y3,y2,y1,y0)	\
-  do {								\
-    int _c1, _c2, _c3;						\
-    r0 = x0 + y0;						\
-    _c1 = r0 < x0;						\
-    r1 = x1 + y1;						\
-    _c2 = r1 < x1;						\
-    r1 += _c1;							\
-    _c2 |= r1 < _c1;						\
-    r2 = x2 + y2;						\
-    _c3 = r2 < x2;						\
-    r2 += _c2;							\
-    _c3 |= r2 < _c2;						\
-    r3 = x3 + y3 + _c3;						\
-  } while (0)
-#endif
-
-#ifndef __FP_FRAC_SUB_4
-#define __FP_FRAC_SUB_4(r3,r2,r1,r0,x3,x2,x1,x0,y3,y2,y1,y0)	\
-  do {								\
-    int _c1, _c2, _c3;						\
-    r0 = x0 - y0;						\
-    _c1 = r0 > x0;						\
-    r1 = x1 - y1;						\
-    _c2 = r1 > x1;						\
-    r1 -= _c1;							\
-    _c2 |= r1 > _c1;						\
-    r2 = x2 - y2;						\
-    _c3 = r2 > x2;						\
-    r2 -= _c2;							\
-    _c3 |= r2 > _c2;						\
-    r3 = x3 - y3 - _c3;						\
-  } while (0)
-#endif
-
-#ifndef __FP_FRAC_ADDI_4
-/* I always wanted to be a lisp programmer :-> */
-#define __FP_FRAC_ADDI_4(x3,x2,x1,x0,i)                                 \
-  (x3 += ((x2 += ((x1 += ((x0 += i) < x0)) < x1) < x2)))
-#endif
-
-/* Convert FP values between word sizes. This appears to be more
- * complicated than I'd have expected it to be, so these might be
- * wrong... These macros are in any case somewhat bogus because they
- * use information about what various FRAC_n variables look like
- * internally [eg, that 2 word vars are X_f0 and x_f1]. But so do
- * the ones in op-2.h and op-1.h.
- */
-#define _FP_FRAC_CONV_1_4(dfs, sfs, D, S)                               \
-   do {                                                                 \
-     _FP_FRAC_SRS_4(S, (_FP_WFRACBITS_##sfs - _FP_WFRACBITS_##dfs),     \
-                        _FP_WFRACBITS_##sfs);                           \
-     D##_f = S##_f[0];                                                   \
-  } while (0)
-
-#define _FP_FRAC_CONV_2_4(dfs, sfs, D, S)                               \
-   do {                                                                 \
-     _FP_FRAC_SRS_4(S, (_FP_WFRACBITS_##sfs - _FP_WFRACBITS_##dfs),     \
-                        _FP_WFRACBITS_##sfs);                           \
-     D##_f0 = S##_f[0];                                                  \
-     D##_f1 = S##_f[1];                                                  \
-  } while (0)
-
-/* Assembly/disassembly for converting to/from integral types.
- * No shifting or overflow handled here.
- */
-/* Put the FP value X into r, which is an integer of size rsize. */
-#define _FP_FRAC_ASSEMBLE_4(r, X, rsize)                                \
-  do {                                                                  \
-    if (rsize <= _FP_W_TYPE_SIZE)                                       \
-      r = X##_f[0];                                                     \
-    else if (rsize <= 2*_FP_W_TYPE_SIZE)                                \
-    {                                                                   \
-      r = X##_f[1];                                                     \
-      r <<= _FP_W_TYPE_SIZE;                                            \
-      r += X##_f[0];                                                    \
-    }                                                                   \
-    else                                                                \
-    {                                                                   \
-      /* I'm feeling lazy so we deal with int == 3words (implausible)*/ \
-      /* and int == 4words as a single case.                         */ \
-      r = X##_f[3];                                                     \
-      r <<= _FP_W_TYPE_SIZE;                                            \
-      r += X##_f[2];                                                    \
-      r <<= _FP_W_TYPE_SIZE;                                            \
-      r += X##_f[1];                                                    \
-      r <<= _FP_W_TYPE_SIZE;                                            \
-      r += X##_f[0];                                                    \
-    }                                                                   \
-  } while (0)
-
-/* "No disassemble Number Five!" */
-/* move an integer of size rsize into X's fractional part. We rely on
- * the _f[] array consisting of words of size _FP_W_TYPE_SIZE to avoid
- * having to mask the values we store into it.
- */
-#define _FP_FRAC_DISASSEMBLE_4(X, r, rsize)                             \
-  do {                                                                  \
-    X##_f[0] = r;                                                       \
-    X##_f[1] = (rsize <= _FP_W_TYPE_SIZE ? 0 : r >> _FP_W_TYPE_SIZE);   \
-    X##_f[2] = (rsize <= 2*_FP_W_TYPE_SIZE ? 0 : r >> 2*_FP_W_TYPE_SIZE); \
-    X##_f[3] = (rsize <= 3*_FP_W_TYPE_SIZE ? 0 : r >> 3*_FP_W_TYPE_SIZE); \
-  } while (0)
-
-#define _FP_FRAC_CONV_4_1(dfs, sfs, D, S)                               \
-   do {                                                                 \
-     D##_f[0] = S##_f;                                                  \
-     D##_f[1] = D##_f[2] = D##_f[3] = 0;                                \
-     _FP_FRAC_SLL_4(D, (_FP_WFRACBITS_##dfs - _FP_WFRACBITS_##sfs));    \
-   } while (0)
-
-#define _FP_FRAC_CONV_4_2(dfs, sfs, D, S)                               \
-   do {                                                                 \
-     D##_f[0] = S##_f0;                                                 \
-     D##_f[1] = S##_f1;                                                 \
-     D##_f[2] = D##_f[3] = 0;                                           \
-     _FP_FRAC_SLL_4(D, (_FP_WFRACBITS_##dfs - _FP_WFRACBITS_##sfs));    \
-   } while (0)
-
-/* FIXME! This has to be written */
-#define _FP_SQRT_MEAT_4(R, S, T, X, q)
diff --git a/arch/powerpc/math-emu/op-common.h b/arch/powerpc/math-emu/op-common.h
deleted file mode 100644
index afb82b6..0000000
--- a/arch/powerpc/math-emu/op-common.h
+++ /dev/null
@@ -1,688 +0,0 @@
-#define _FP_DECL(wc, X)			\
-  _FP_I_TYPE X##_c, X##_s, X##_e;	\
-  _FP_FRAC_DECL_##wc(X)
-
-/*
- * Finish truely unpacking a native fp value by classifying the kind
- * of fp value and normalizing both the exponent and the fraction.
- */
-
-#define _FP_UNPACK_CANONICAL(fs, wc, X)					\
-do {									\
-  switch (X##_e)							\
-  {									\
-  default:								\
-    _FP_FRAC_HIGH_##wc(X) |= _FP_IMPLBIT_##fs;				\
-    _FP_FRAC_SLL_##wc(X, _FP_WORKBITS);					\
-    X##_e -= _FP_EXPBIAS_##fs;						\
-    X##_c = FP_CLS_NORMAL;						\
-    break;								\
-									\
-  case 0:								\
-    if (_FP_FRAC_ZEROP_##wc(X))						\
-      X##_c = FP_CLS_ZERO;						\
-    else								\
-      {									\
-	/* a denormalized number */					\
-	_FP_I_TYPE _shift;						\
-	_FP_FRAC_CLZ_##wc(_shift, X);					\
-	_shift -= _FP_FRACXBITS_##fs;					\
-	_FP_FRAC_SLL_##wc(X, (_shift+_FP_WORKBITS));			\
-	X##_e -= _FP_EXPBIAS_##fs - 1 + _shift;				\
-	X##_c = FP_CLS_NORMAL;						\
-      }									\
-    break;								\
-									\
-  case _FP_EXPMAX_##fs:							\
-    if (_FP_FRAC_ZEROP_##wc(X))						\
-      X##_c = FP_CLS_INF;						\
-    else								\
-      /* we don't differentiate between signaling and quiet nans */	\
-      X##_c = FP_CLS_NAN;						\
-    break;								\
-  }									\
-} while (0)
-
-
-/*
- * Before packing the bits back into the native fp result, take care
- * of such mundane things as rounding and overflow.  Also, for some
- * kinds of fp values, the original parts may not have been fully
- * extracted -- but that is ok, we can regenerate them now.
- */
-
-#define _FP_PACK_CANONICAL(fs, wc, X)				\
-({int __ret = 0;						\
-  switch (X##_c)						\
-  {								\
-  case FP_CLS_NORMAL:						\
-    X##_e += _FP_EXPBIAS_##fs;					\
-    if (X##_e > 0)						\
-      {								\
-	__ret |= _FP_ROUND(wc, X);				\
-	if (_FP_FRAC_OVERP_##wc(fs, X))				\
-	  {							\
-	    _FP_FRAC_SRL_##wc(X, (_FP_WORKBITS+1));		\
-	    X##_e++;						\
-	  }							\
-	else							\
-	  _FP_FRAC_SRL_##wc(X, _FP_WORKBITS);			\
-	if (X##_e >= _FP_EXPMAX_##fs)				\
-	  {							\
-	    /* overflow to infinity */				\
-	    X##_e = _FP_EXPMAX_##fs;				\
-	    _FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);		\
-            __ret |= EFLAG_OVERFLOW;				\
-	  }							\
-      }								\
-    else							\
-      {								\
-	/* we've got a denormalized number */			\
-	X##_e = -X##_e + 1;					\
-	if (X##_e <= _FP_WFRACBITS_##fs)			\
-	  {							\
-	    _FP_FRAC_SRS_##wc(X, X##_e, _FP_WFRACBITS_##fs);	\
-	    _FP_FRAC_SLL_##wc(X, 1);				\
-	    if (_FP_FRAC_OVERP_##wc(fs, X))			\
-	      {							\
-	        X##_e = 1;					\
-	        _FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);	\
-	      }							\
-	    else						\
-	      {							\
-		X##_e = 0;					\
-		_FP_FRAC_SRL_##wc(X, _FP_WORKBITS+1);		\
-                __ret |= EFLAG_UNDERFLOW;			\
-	      }							\
-	  }							\
-	else							\
-	  {							\
-	    /* underflow to zero */				\
-	    X##_e = 0;						\
-	    _FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);		\
-            __ret |= EFLAG_UNDERFLOW;				\
-	  }							\
-      }								\
-    break;							\
-								\
-  case FP_CLS_ZERO:						\
-    X##_e = 0;							\
-    _FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);			\
-    break;							\
-								\
-  case FP_CLS_INF:						\
-    X##_e = _FP_EXPMAX_##fs;					\
-    _FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);			\
-    break;							\
-								\
-  case FP_CLS_NAN:						\
-    X##_e = _FP_EXPMAX_##fs;					\
-    if (!_FP_KEEPNANFRACP)					\
-      {								\
-	_FP_FRAC_SET_##wc(X, _FP_NANFRAC_##fs);			\
-	X##_s = 0;						\
-      }								\
-    else							\
-      _FP_FRAC_HIGH_##wc(X) |= _FP_QNANBIT_##fs;		\
-    break;							\
-  }								\
-  __ret;							\
-})
-
-
-/*
- * Main addition routine.  The input values should be cooked.
- */
-
-#define _FP_ADD(fs, wc, R, X, Y)					     \
-do {									     \
-  switch (_FP_CLS_COMBINE(X##_c, Y##_c))				     \
-  {									     \
-  case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NORMAL):			     \
-    {									     \
-      /* shift the smaller number so that its exponent matches the larger */ \
-      _FP_I_TYPE diff = X##_e - Y##_e;					     \
-									     \
-      if (diff < 0)							     \
-	{								     \
-	  diff = -diff;							     \
-	  if (diff <= _FP_WFRACBITS_##fs)				     \
-	    _FP_FRAC_SRS_##wc(X, diff, _FP_WFRACBITS_##fs);		     \
-	  else if (!_FP_FRAC_ZEROP_##wc(X))				     \
-	    _FP_FRAC_SET_##wc(X, _FP_MINFRAC_##wc);			     \
-	  else								     \
-	    _FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);			     \
-	  R##_e = Y##_e;						     \
-	}								     \
-      else								     \
-	{								     \
-	  if (diff > 0)							     \
-	    {								     \
-	      if (diff <= _FP_WFRACBITS_##fs)				     \
-	        _FP_FRAC_SRS_##wc(Y, diff, _FP_WFRACBITS_##fs);		     \
-	      else if (!_FP_FRAC_ZEROP_##wc(Y))				     \
-	        _FP_FRAC_SET_##wc(Y, _FP_MINFRAC_##wc);			     \
-	      else							     \
-	        _FP_FRAC_SET_##wc(Y, _FP_ZEROFRAC_##wc);		     \
-	    }								     \
-	  R##_e = X##_e;						     \
-	}								     \
-									     \
-      R##_c = FP_CLS_NORMAL;						     \
-									     \
-      if (X##_s == Y##_s)						     \
-	{								     \
-	  R##_s = X##_s;						     \
-	  _FP_FRAC_ADD_##wc(R, X, Y);					     \
-	  if (_FP_FRAC_OVERP_##wc(fs, R))				     \
-	    {								     \
-	      _FP_FRAC_SRS_##wc(R, 1, _FP_WFRACBITS_##fs);		     \
-	      R##_e++;							     \
-	    }								     \
-	}								     \
-      else								     \
-	{								     \
-	  R##_s = X##_s;						     \
-	  _FP_FRAC_SUB_##wc(R, X, Y);					     \
-	  if (_FP_FRAC_ZEROP_##wc(R))					     \
-	    {								     \
-	      /* return an exact zero */				     \
-	      if (FP_ROUNDMODE == FP_RND_MINF)				     \
-		R##_s |= Y##_s;						     \
-	      else							     \
-		R##_s &= Y##_s;						     \
-	      R##_c = FP_CLS_ZERO;					     \
-	    }								     \
-	  else								     \
-	    {								     \
-	      if (_FP_FRAC_NEGP_##wc(R))				     \
-		{							     \
-		  _FP_FRAC_SUB_##wc(R, Y, X);				     \
-		  R##_s = Y##_s;					     \
-		}							     \
-									     \
-	      /* renormalize after subtraction */			     \
-	      _FP_FRAC_CLZ_##wc(diff, R);				     \
-	      diff -= _FP_WFRACXBITS_##fs;				     \
-	      if (diff)							     \
-		{							     \
-		  R##_e -= diff;					     \
-		  _FP_FRAC_SLL_##wc(R, diff);				     \
-		}							     \
-	    }								     \
-	}								     \
-      break;								     \
-    }									     \
-									     \
-  case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NAN):				     \
-    _FP_CHOOSENAN(fs, wc, R, X, Y);					     \
-    break;								     \
-									     \
-  case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO):			     \
-    R##_e = X##_e;							     \
-  case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NORMAL):			     \
-  case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_INF):				     \
-  case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_ZERO):				     \
-    _FP_FRAC_COPY_##wc(R, X);						     \
-    R##_s = X##_s;							     \
-    R##_c = X##_c;							     \
-    break;								     \
-									     \
-  case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NORMAL):			     \
-    R##_e = Y##_e;							     \
-  case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NAN):			     \
-  case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NAN):				     \
-  case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NAN):				     \
-    _FP_FRAC_COPY_##wc(R, Y);						     \
-    R##_s = Y##_s;							     \
-    R##_c = Y##_c;							     \
-    break;								     \
-									     \
-  case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_INF):				     \
-    if (X##_s != Y##_s)							     \
-      {									     \
-	/* +INF + -INF => NAN */					     \
-	_FP_FRAC_SET_##wc(R, _FP_NANFRAC_##fs);				     \
-	R##_s = X##_s ^ Y##_s;						     \
-	R##_c = FP_CLS_NAN;						     \
-	break;								     \
-      }									     \
-    /* FALLTHRU */							     \
-									     \
-  case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL):			     \
-  case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_ZERO):				     \
-    R##_s = X##_s;							     \
-    R##_c = FP_CLS_INF;							     \
-    break;								     \
-									     \
-  case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_INF):			     \
-  case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_INF):				     \
-    R##_s = Y##_s;							     \
-    R##_c = FP_CLS_INF;							     \
-    break;								     \
-									     \
-  case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_ZERO):			     \
-    /* make sure the sign is correct */					     \
-    if (FP_ROUNDMODE == FP_RND_MINF)					     \
-      R##_s = X##_s | Y##_s;						     \
-    else								     \
-      R##_s = X##_s & Y##_s;						     \
-    R##_c = FP_CLS_ZERO;						     \
-    break;								     \
-									     \
-  default:								     \
-    abort();								     \
-  }									     \
-} while (0)
-
-
-/*
- * Main negation routine.  FIXME -- when we care about setting exception
- * bits reliably, this will not do.  We should examine all of the fp classes.
- */
-
-#define _FP_NEG(fs, wc, R, X)		\
-  do {					\
-    _FP_FRAC_COPY_##wc(R, X);		\
-    R##_c = X##_c;			\
-    R##_e = X##_e;			\
-    R##_s = 1 ^ X##_s;			\
-  } while (0)
-
-
-/*
- * Main multiplication routine.  The input values should be cooked.
- */
-
-#define _FP_MUL(fs, wc, R, X, Y)			\
-do {							\
-  R##_s = X##_s ^ Y##_s;				\
-  switch (_FP_CLS_COMBINE(X##_c, Y##_c))		\
-  {							\
-  case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NORMAL):	\
-    R##_c = FP_CLS_NORMAL;				\
-    R##_e = X##_e + Y##_e + 1;				\
-							\
-    _FP_MUL_MEAT_##fs(R,X,Y);				\
-							\
-    if (_FP_FRAC_OVERP_##wc(fs, R))			\
-      _FP_FRAC_SRS_##wc(R, 1, _FP_WFRACBITS_##fs);	\
-    else						\
-      R##_e--;						\
-    break;						\
-							\
-  case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NAN):		\
-    _FP_CHOOSENAN(fs, wc, R, X, Y);			\
-    break;						\
-							\
-  case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NORMAL):	\
-  case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_INF):		\
-  case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_ZERO):		\
-    R##_s = X##_s;					\
-							\
-  case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_INF):		\
-  case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL):	\
-  case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NORMAL):	\
-  case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_ZERO):	\
-    _FP_FRAC_COPY_##wc(R, X);				\
-    R##_c = X##_c;					\
-    break;						\
-							\
-  case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NAN):	\
-  case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NAN):		\
-  case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NAN):		\
-    R##_s = Y##_s;					\
-							\
-  case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_INF):	\
-  case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO):	\
-    _FP_FRAC_COPY_##wc(R, Y);				\
-    R##_c = Y##_c;					\
-    break;						\
-							\
-  case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_ZERO):		\
-  case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_INF):		\
-    R##_c = FP_CLS_NAN;					\
-    _FP_FRAC_SET_##wc(R, _FP_NANFRAC_##fs);		\
-    break;						\
-							\
-  default:						\
-    abort();						\
-  }							\
-} while (0)
-
-
-/*
- * Main division routine.  The input values should be cooked.
- */
-
-#define _FP_DIV(fs, wc, R, X, Y)			\
-do {							\
-  R##_s = X##_s ^ Y##_s;				\
-  switch (_FP_CLS_COMBINE(X##_c, Y##_c))		\
-  {							\
-  case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NORMAL):	\
-    R##_c = FP_CLS_NORMAL;				\
-    R##_e = X##_e - Y##_e;				\
-							\
-    _FP_DIV_MEAT_##fs(R,X,Y);				\
-    break;						\
-							\
-  case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NAN):		\
-    _FP_CHOOSENAN(fs, wc, R, X, Y);			\
-    break;						\
-							\
-  case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NORMAL):	\
-  case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_INF):		\
-  case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_ZERO):		\
-    R##_s = X##_s;					\
-    _FP_FRAC_COPY_##wc(R, X);				\
-    R##_c = X##_c;					\
-    break;						\
-							\
-  case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NAN):	\
-  case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NAN):		\
-  case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NAN):		\
-    R##_s = Y##_s;					\
-    _FP_FRAC_COPY_##wc(R, Y);				\
-    R##_c = Y##_c;					\
-    break;						\
-							\
-  case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_INF):	\
-  case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_INF):		\
-  case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NORMAL):	\
-    R##_c = FP_CLS_ZERO;				\
-    break;						\
-							\
-  case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO):	\
-  case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_ZERO):		\
-  case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL):	\
-    R##_c = FP_CLS_INF;					\
-    break;						\
-							\
-  case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_INF):		\
-  case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_ZERO):	\
-    R##_c = FP_CLS_NAN;					\
-    _FP_FRAC_SET_##wc(R, _FP_NANFRAC_##fs);		\
-    break;						\
-							\
-  default:						\
-    abort();						\
-  }							\
-} while (0)
-
-
-/*
- * Main differential comparison routine.  The inputs should be raw not
- * cooked.  The return is -1,0,1 for normal values, 2 otherwise.
- */
-
-#define _FP_CMP(fs, wc, ret, X, Y, un)					\
-  do {									\
-    /* NANs are unordered */						\
-    if ((X##_e == _FP_EXPMAX_##fs && !_FP_FRAC_ZEROP_##wc(X))		\
-	|| (Y##_e == _FP_EXPMAX_##fs && !_FP_FRAC_ZEROP_##wc(Y)))	\
-      {									\
-	ret = un;							\
-      }									\
-    else								\
-      {									\
-        int __x_zero = (!X##_e && _FP_FRAC_ZEROP_##wc(X)) ? 1 : 0;	\
-        int __y_zero = (!Y##_e && _FP_FRAC_ZEROP_##wc(Y)) ? 1 : 0;	\
-									\
-	if (__x_zero && __y_zero)					\
-	  ret = 0;							\
-	else if (__x_zero)						\
-	  ret = Y##_s ? 1 : -1;						\
-	else if (__y_zero)						\
-	  ret = X##_s ? -1 : 1;						\
-	else if (X##_s != Y##_s)					\
-	  ret = X##_s ? -1 : 1;						\
-	else if (X##_e > Y##_e)						\
-	  ret = X##_s ? -1 : 1;						\
-	else if (X##_e < Y##_e)						\
-	  ret = X##_s ? 1 : -1;						\
-	else if (_FP_FRAC_GT_##wc(X, Y))				\
-	  ret = X##_s ? -1 : 1;						\
-	else if (_FP_FRAC_GT_##wc(Y, X))				\
-	  ret = X##_s ? 1 : -1;						\
-	else								\
-	  ret = 0;							\
-      }									\
-  } while (0)
-
-
-/* Simplification for strict equality.  */
-
-#define _FP_CMP_EQ(fs, wc, ret, X, Y)					  \
-  do {									  \
-    /* NANs are unordered */						  \
-    if ((X##_e == _FP_EXPMAX_##fs && !_FP_FRAC_ZEROP_##wc(X))		  \
-	|| (Y##_e == _FP_EXPMAX_##fs && !_FP_FRAC_ZEROP_##wc(Y)))	  \
-      {									  \
-	ret = 1;							  \
-      }									  \
-    else								  \
-      {									  \
-	ret = !(X##_e == Y##_e						  \
-		&& _FP_FRAC_EQ_##wc(X, Y)				  \
-		&& (X##_s == Y##_s || !X##_e && _FP_FRAC_ZEROP_##wc(X))); \
-      }									  \
-  } while (0)
-
-/*
- * Main square root routine.  The input value should be cooked.
- */
-
-#define _FP_SQRT(fs, wc, R, X)						\
-do {									\
-    _FP_FRAC_DECL_##wc(T); _FP_FRAC_DECL_##wc(S);			\
-    _FP_W_TYPE q;							\
-    switch (X##_c)							\
-    {									\
-    case FP_CLS_NAN:							\
-    	R##_s = 0;							\
-    	R##_c = FP_CLS_NAN;						\
-    	_FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);			\
-    	break;								\
-    case FP_CLS_INF:							\
-    	if (X##_s)							\
-    	  {								\
-    	    R##_s = 0;							\
-	    R##_c = FP_CLS_NAN; /* sNAN */				\
-    	  }								\
-    	else								\
-    	  {								\
-    	    R##_s = 0;							\
-    	    R##_c = FP_CLS_INF; /* sqrt(+inf) = +inf */			\
-    	  }								\
-    	break;								\
-    case FP_CLS_ZERO:							\
-	R##_s = X##_s;							\
-    	R##_c = FP_CLS_ZERO; /* sqrt(+-0) = +-0 */			\
-	break;								\
-    case FP_CLS_NORMAL:							\
-    	R##_s = 0;							\
-        if (X##_s)							\
-          {								\
-	    R##_c = FP_CLS_NAN; /* sNAN */				\
-	    break;							\
-          }								\
-    	R##_c = FP_CLS_NORMAL;						\
-        if (X##_e & 1)							\
-          _FP_FRAC_SLL_##wc(X, 1);					\
-        R##_e = X##_e >> 1;						\
-        _FP_FRAC_SET_##wc(S, _FP_ZEROFRAC_##wc);			\
-        _FP_FRAC_SET_##wc(R, _FP_ZEROFRAC_##wc);			\
-        q = _FP_OVERFLOW_##fs;						\
-        _FP_FRAC_SLL_##wc(X, 1);					\
-        _FP_SQRT_MEAT_##wc(R, S, T, X, q);				\
-        _FP_FRAC_SRL_##wc(R, 1);					\
-    }									\
-  } while (0)
-
-/*
- * Convert from FP to integer
- */
-
-/* "When a NaN, infinity, large positive argument >= 2147483648.0, or
- * large negative argument <= -2147483649.0 is converted to an integer,
- * the invalid_current bit...should be set and fp_exception_IEEE_754 should
- * be raised. If the floating point invalid trap is disabled, no trap occurs
- * and a numerical result is generated: if the sign bit of the operand
- * is 0, the result is 2147483647; if the sign bit of the operand is 1,
- * the result is -2147483648."
- * Similarly for conversion to extended ints, except that the boundaries
- * are >= 2^63, <= -(2^63 + 1), and the results are 2^63 + 1 for s=0 and
- * -2^63 for s=1.
- * -- SPARC Architecture Manual V9, Appendix B, which specifies how
- * SPARCs resolve implementation dependencies in the IEEE-754 spec.
- * I don't believe that the code below follows this. I'm not even sure
- * it's right!
- * It doesn't cope with needing to convert to an n bit integer when there
- * is no n bit integer type. Fortunately gcc provides long long so this
- * isn't a problem for sparc32.
- * I have, however, fixed its NaN handling to conform as above.
- *         -- PMM 02/1998
- * NB: rsigned is not 'is r declared signed?' but 'should the value stored
- * in r be signed or unsigned?'. r is always(?) declared unsigned.
- * Comments below are mine, BTW -- PMM
- */
-#define _FP_TO_INT(fs, wc, r, X, rsize, rsigned)			\
-  do {									\
-    switch (X##_c)							\
-      {									\
-      case FP_CLS_NORMAL:						\
-	if (X##_e < 0)							\
-	  {								\
-	  /* case FP_CLS_NAN: see above! */				\
-	  case FP_CLS_ZERO:						\
-	    r = 0;							\
-	  }								\
-	else if (X##_e >= rsize - (rsigned != 0))			\
-	  {	/* overflow */						\
-	  case FP_CLS_NAN:                                              \
-          case FP_CLS_INF:						\
-	    if (rsigned)						\
-	      {								\
-		r = 1;							\
-		r <<= rsize - 1;					\
-		r -= 1 - X##_s;						\
-	      }								\
-	    else							\
-	      {								\
-		r = 0;							\
-		if (!X##_s)						\
-		  r = ~r;						\
-	      }								\
-	  }								\
-	else								\
-	  {								\
-	    if (_FP_W_TYPE_SIZE*wc < rsize)				\
-	      {								\
-		_FP_FRAC_ASSEMBLE_##wc(r, X, rsize);			\
-		r <<= X##_e - _FP_WFRACBITS_##fs;			\
-	      }								\
-	    else							\
-	      {								\
-		if (X##_e >= _FP_WFRACBITS_##fs)			\
-		  _FP_FRAC_SLL_##wc(X, (X##_e - _FP_WFRACBITS_##fs + 1));\
-		else							\
-		  _FP_FRAC_SRL_##wc(X, (_FP_WFRACBITS_##fs - X##_e - 1));\
-		_FP_FRAC_ASSEMBLE_##wc(r, X, rsize);			\
-	      }								\
-	    if (rsigned && X##_s)					\
-	      r = -r;							\
-	  }								\
-	break;								\
-      }									\
-  } while (0)
-
-#define _FP_FROM_INT(fs, wc, X, r, rsize, rtype)			\
-  do {									\
-    if (r)								\
-      {									\
-	X##_c = FP_CLS_NORMAL;						\
-									\
-	if ((X##_s = (r < 0)))						\
-	  r = -r;							\
-	/* Note that `r' is now considered unsigned, so we don't have	\
-	   to worry about the single signed overflow case.  */		\
-									\
-	if (rsize <= _FP_W_TYPE_SIZE)					\
-	  __FP_CLZ(X##_e, r);						\
-	else								\
-	  __FP_CLZ_2(X##_e, (_FP_W_TYPE)(r >> _FP_W_TYPE_SIZE), 	\
-		     (_FP_W_TYPE)r);					\
-	if (rsize < _FP_W_TYPE_SIZE)					\
-		X##_e -= (_FP_W_TYPE_SIZE - rsize);			\
-	X##_e = rsize - X##_e - 1;					\
-									\
-	if (_FP_FRACBITS_##fs < rsize && _FP_WFRACBITS_##fs < X##_e)	\
-	  __FP_FRAC_SRS_1(r, (X##_e - _FP_WFRACBITS_##fs), rsize);	\
-	r &= ~((_FP_W_TYPE)1 << X##_e);					\
-	_FP_FRAC_DISASSEMBLE_##wc(X, ((unsigned rtype)r), rsize);	\
-	_FP_FRAC_SLL_##wc(X, (_FP_WFRACBITS_##fs - X##_e - 1));		\
-      }									\
-    else								\
-      {									\
-	X##_c = FP_CLS_ZERO, X##_s = 0;					\
-      }									\
-  } while (0)
-
-
-#define FP_CONV(dfs,sfs,dwc,swc,D,S)			\
-  do {							\
-    _FP_FRAC_CONV_##dwc##_##swc(dfs, sfs, D, S);	\
-    D##_e = S##_e;					\
-    D##_c = S##_c;					\
-    D##_s = S##_s;					\
-  } while (0)
-
-/*
- * Helper primitives.
- */
-
-/* Count leading zeros in a word.  */
-
-#ifndef __FP_CLZ
-#if _FP_W_TYPE_SIZE < 64
-/* this is just to shut the compiler up about shifts > word length -- PMM 02/1998 */
-#define __FP_CLZ(r, x)				\
-  do {						\
-    _FP_W_TYPE _t = (x);			\
-    r = _FP_W_TYPE_SIZE - 1;			\
-    if (_t > 0xffff) r -= 16;			\
-    if (_t > 0xffff) _t >>= 16;			\
-    if (_t > 0xff) r -= 8;			\
-    if (_t > 0xff) _t >>= 8;			\
-    if (_t & 0xf0) r -= 4;			\
-    if (_t & 0xf0) _t >>= 4;			\
-    if (_t & 0xc) r -= 2;			\
-    if (_t & 0xc) _t >>= 2;			\
-    if (_t & 0x2) r -= 1;			\
-  } while (0)
-#else /* not _FP_W_TYPE_SIZE < 64 */
-#define __FP_CLZ(r, x)				\
-  do {						\
-    _FP_W_TYPE _t = (x);			\
-    r = _FP_W_TYPE_SIZE - 1;			\
-    if (_t > 0xffffffff) r -= 32;		\
-    if (_t > 0xffffffff) _t >>= 32;		\
-    if (_t > 0xffff) r -= 16;			\
-    if (_t > 0xffff) _t >>= 16;			\
-    if (_t > 0xff) r -= 8;			\
-    if (_t > 0xff) _t >>= 8;			\
-    if (_t & 0xf0) r -= 4;			\
-    if (_t & 0xf0) _t >>= 4;			\
-    if (_t & 0xc) r -= 2;			\
-    if (_t & 0xc) _t >>= 2;			\
-    if (_t & 0x2) r -= 1;			\
-  } while (0)
-#endif /* not _FP_W_TYPE_SIZE < 64 */
-#endif /* ndef __FP_CLZ */
-
-#define _FP_DIV_HELP_imm(q, r, n, d)		\
-  do {						\
-    q = n / d, r = n % d;			\
-  } while (0)
-
diff --git a/arch/powerpc/math-emu/single.h b/arch/powerpc/math-emu/single.h
deleted file mode 100644
index f19d994..0000000
--- a/arch/powerpc/math-emu/single.h
+++ /dev/null
@@ -1,66 +0,0 @@
-/*
- * Definitions for IEEE Single Precision
- */
-
-#if _FP_W_TYPE_SIZE < 32
-#error "Here's a nickel kid.  Go buy yourself a real computer."
-#endif
-
-#define _FP_FRACBITS_S		24
-#define _FP_FRACXBITS_S		(_FP_W_TYPE_SIZE - _FP_FRACBITS_S)
-#define _FP_WFRACBITS_S		(_FP_WORKBITS + _FP_FRACBITS_S)
-#define _FP_WFRACXBITS_S	(_FP_W_TYPE_SIZE - _FP_WFRACBITS_S)
-#define _FP_EXPBITS_S		8
-#define _FP_EXPBIAS_S		127
-#define _FP_EXPMAX_S		255
-#define _FP_QNANBIT_S		((_FP_W_TYPE)1 << (_FP_FRACBITS_S-2))
-#define _FP_IMPLBIT_S		((_FP_W_TYPE)1 << (_FP_FRACBITS_S-1))
-#define _FP_OVERFLOW_S		((_FP_W_TYPE)1 << (_FP_WFRACBITS_S))
-
-/* The implementation of _FP_MUL_MEAT_S and _FP_DIV_MEAT_S should be
-   chosen by the target machine.  */
-
-union _FP_UNION_S
-{
-  float flt;
-  struct {
-#if __BYTE_ORDER == __BIG_ENDIAN
-    unsigned sign : 1;
-    unsigned exp  : _FP_EXPBITS_S;
-    unsigned frac : _FP_FRACBITS_S - (_FP_IMPLBIT_S != 0);
-#else
-    unsigned frac : _FP_FRACBITS_S - (_FP_IMPLBIT_S != 0);
-    unsigned exp  : _FP_EXPBITS_S;
-    unsigned sign : 1;
-#endif
-  } bits __attribute__((packed));
-};
-
-#define FP_DECL_S(X)		_FP_DECL(1,X)
-#define FP_UNPACK_RAW_S(X,val)	_FP_UNPACK_RAW_1(S,X,val)
-#define FP_PACK_RAW_S(val,X)	_FP_PACK_RAW_1(S,val,X)
-
-#define FP_UNPACK_S(X,val)		\
-  do {					\
-    _FP_UNPACK_RAW_1(S,X,val);		\
-    _FP_UNPACK_CANONICAL(S,1,X);	\
-  } while (0)
-
-#define FP_PACK_S(val,X)		\
-  do {					\
-    _FP_PACK_CANONICAL(S,1,X);		\
-    _FP_PACK_RAW_1(S,val,X);		\
-  } while (0)
-
-#define FP_NEG_S(R,X)		_FP_NEG(S,1,R,X)
-#define FP_ADD_S(R,X,Y)		_FP_ADD(S,1,R,X,Y)
-#define FP_SUB_S(R,X,Y)		_FP_SUB(S,1,R,X,Y)
-#define FP_MUL_S(R,X,Y)		_FP_MUL(S,1,R,X,Y)
-#define FP_DIV_S(R,X,Y)		_FP_DIV(S,1,R,X,Y)
-#define FP_SQRT_S(R,X)		_FP_SQRT(S,1,R,X)
-
-#define FP_CMP_S(r,X,Y,un)	_FP_CMP(S,1,r,X,Y,un)
-#define FP_CMP_EQ_S(r,X,Y)	_FP_CMP_EQ(S,1,r,X,Y)
-
-#define FP_TO_INT_S(r,X,rsz,rsg)  _FP_TO_INT(S,1,r,X,rsz,rsg)
-#define FP_FROM_INT_S(X,r,rs,rt)  _FP_FROM_INT(S,1,X,r,rs,rt)
diff --git a/arch/powerpc/math-emu/soft-fp.h b/arch/powerpc/math-emu/soft-fp.h
deleted file mode 100644
index cca3959..0000000
--- a/arch/powerpc/math-emu/soft-fp.h
+++ /dev/null
@@ -1,104 +0,0 @@
-#ifndef SOFT_FP_H
-#define SOFT_FP_H
-
-#include "sfp-machine.h"
-
-#define _FP_WORKBITS		3
-#define _FP_WORK_LSB		((_FP_W_TYPE)1 << 3)
-#define _FP_WORK_ROUND		((_FP_W_TYPE)1 << 2)
-#define _FP_WORK_GUARD		((_FP_W_TYPE)1 << 1)
-#define _FP_WORK_STICKY		((_FP_W_TYPE)1 << 0)
-
-#ifndef FP_RND_NEAREST
-# define FP_RND_NEAREST		0
-# define FP_RND_ZERO		1
-# define FP_RND_PINF		2
-# define FP_RND_MINF		3
-#ifndef FP_ROUNDMODE
-# define FP_ROUNDMODE		FP_RND_NEAREST
-#endif
-#endif
-
-#define _FP_ROUND_NEAREST(wc, X)			\
-({  int __ret = 0;					\
-    int __frac = _FP_FRAC_LOW_##wc(X) & 15;		\
-    if (__frac & 7) {					\
-      __ret = EFLAG_INEXACT;				\
-      if ((__frac & 7) != _FP_WORK_ROUND)		\
-        _FP_FRAC_ADDI_##wc(X, _FP_WORK_ROUND);		\
-      else if (__frac & _FP_WORK_LSB)			\
-        _FP_FRAC_ADDI_##wc(X, _FP_WORK_ROUND);		\
-    }							\
-    __ret;						\
-})
-
-#define _FP_ROUND_ZERO(wc, X)				\
-({  int __ret = 0;					\
-    if (_FP_FRAC_LOW_##wc(X) & 7)			\
-      __ret = EFLAG_INEXACT;				\
-    __ret;						\
-})
-
-#define _FP_ROUND_PINF(wc, X)				\
-({  int __ret = EFLAG_INEXACT;				\
-    if (!X##_s && (_FP_FRAC_LOW_##wc(X) & 7))		\
-      _FP_FRAC_ADDI_##wc(X, _FP_WORK_LSB);		\
-    else __ret = 0;					\
-    __ret;						\
-})
-
-#define _FP_ROUND_MINF(wc, X)				\
-({  int __ret = EFLAG_INEXACT;				\
-    if (X##_s && (_FP_FRAC_LOW_##wc(X) & 7))		\
-      _FP_FRAC_ADDI_##wc(X, _FP_WORK_LSB);		\
-    else __ret = 0;					\
-    __ret;						\
-})
-
-#define _FP_ROUND(wc, X)			\
-({	int __ret = 0;				\
-	switch (FP_ROUNDMODE)			\
-	{					\
-	  case FP_RND_NEAREST:			\
-	    __ret |= _FP_ROUND_NEAREST(wc,X);	\
-	    break;				\
-	  case FP_RND_ZERO:			\
-	    __ret |= _FP_ROUND_ZERO(wc,X);	\
-	    break;				\
-	  case FP_RND_PINF:			\
-	    __ret |= _FP_ROUND_PINF(wc,X);	\
-	    break;				\
-	  case FP_RND_MINF:			\
-	    __ret |= _FP_ROUND_MINF(wc,X);	\
-	    break;				\
-	};					\
-	__ret;					\
-})
-
-#define FP_CLS_NORMAL		0
-#define FP_CLS_ZERO		1
-#define FP_CLS_INF		2
-#define FP_CLS_NAN		3
-
-#define _FP_CLS_COMBINE(x,y)	(((x) << 2) | (y))
-
-#include "op-1.h"
-#include "op-2.h"
-#include "op-4.h"
-#include "op-common.h"
-
-/* Sigh.  Silly things longlong.h needs.  */
-#define UWtype		_FP_W_TYPE
-#define W_TYPE_SIZE	_FP_W_TYPE_SIZE
-
-typedef int SItype __attribute__((mode(SI)));
-typedef int DItype __attribute__((mode(DI)));
-typedef unsigned int USItype __attribute__((mode(SI)));
-typedef unsigned int UDItype __attribute__((mode(DI)));
-#if _FP_W_TYPE_SIZE == 32
-typedef unsigned int UHWtype __attribute__((mode(HI)));
-#elif _FP_W_TYPE_SIZE == 64
-typedef USItype UHWtype;
-#endif
-
-#endif
diff --git a/arch/powerpc/math-emu/stfs.c b/arch/powerpc/math-emu/stfs.c
index 8689aa4..6122147 100644
--- a/arch/powerpc/math-emu/stfs.c
+++ b/arch/powerpc/math-emu/stfs.c
@@ -2,23 +2,24 @@
 #include <linux/errno.h>
 #include <asm/uaccess.h>
 
-#include "soft-fp.h"
-#include "double.h"
-#include "single.h"
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
 
 int
 stfs(void *frS, void *ea)
 {
 	FP_DECL_D(A);
 	FP_DECL_S(R);
+	FP_DECL_EX;
 	float f;
-	int err;
 
 #ifdef DEBUG
 	printk("%s: S %p, ea %p\n", __func__, frS, ea);
 #endif
 
-	__FP_UNPACK_D(A, frS);
+	FP_UNPACK_DP(A, frS);
 
 #ifdef DEBUG
 	printk("A: %ld %lu %lu %ld (%ld)\n", A_s, A_f1, A_f0, A_e, A_c);
@@ -30,12 +31,12 @@
 	printk("R: %ld %lu %ld (%ld)\n", R_s, R_f, R_e, R_c);
 #endif
 
-	err = _FP_PACK_CANONICAL(S, 1, R);
-	if (!err || !__FPU_TRAP_P(err)) {
-		__FP_PACK_RAW_1(S, &f, R);
+	_FP_PACK_CANONICAL(S, 1, R);
+	if (!FP_CUR_EXCEPTIONS || !__FPU_TRAP_P(FP_CUR_EXCEPTIONS)) {
+		_FP_PACK_RAW_1_P(S, &f, R);
 		if (copy_to_user(ea, &f, sizeof(float)))
 			return -EFAULT;
 	}
 
-	return err;
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/types.c b/arch/powerpc/math-emu/types.c
deleted file mode 100644
index e1ed15d..0000000
--- a/arch/powerpc/math-emu/types.c
+++ /dev/null
@@ -1,51 +0,0 @@
-#include "soft-fp.h"
-#include "double.h"
-#include "single.h"
-
-void
-fp_unpack_d(long *_s, unsigned long *_f1, unsigned long *_f0,
-	    long *_e, long *_c, void *val)
-{
-	FP_DECL_D(X);
-
-	__FP_UNPACK_RAW_2(D, X, val);
-
-	_FP_UNPACK_CANONICAL(D, 2, X);
-
-	*_s = X_s;
-	*_f1 = X_f1;
-	*_f0 = X_f0;
-	*_e = X_e;
-	*_c = X_c;
-}
-
-int
-fp_pack_d(void *val, long X_s, unsigned long X_f1,
-	  unsigned long X_f0, long X_e, long X_c)
-{
-	int exc;
-
-	exc = _FP_PACK_CANONICAL(D, 2, X);
-	if (!exc || !__FPU_TRAP_P(exc))
-		__FP_PACK_RAW_2(D, val, X);
-	return exc;
-}
-
-int
-fp_pack_ds(void *val, long X_s, unsigned long X_f1,
-	   unsigned long X_f0, long X_e, long X_c)
-{
-	FP_DECL_S(__X);
-	int exc;
-
-	FP_CONV(S, D, 1, 2, __X, X);
-	exc = _FP_PACK_CANONICAL(S, 1, __X);
-	if (!exc || !__FPU_TRAP_P(exc)) {
-		_FP_UNPACK_CANONICAL(S, 1, __X);
-		FP_CONV(D, S, 2, 1, X, __X);
-		exc |= _FP_PACK_CANONICAL(D, 2, X);
-		if (!exc || !__FPU_TRAP_P(exc))
-			__FP_PACK_RAW_2(D, val, X);
-	}
-	return exc;
-}
diff --git a/arch/powerpc/math-emu/udivmodti4.c b/arch/powerpc/math-emu/udivmodti4.c
index 7e112dc..6172044 100644
--- a/arch/powerpc/math-emu/udivmodti4.c
+++ b/arch/powerpc/math-emu/udivmodti4.c
@@ -1,6 +1,6 @@
 /* This has so very few changes over libgcc2's __udivmoddi4 it isn't funny.  */
 
-#include "soft-fp.h"
+#include <math-emu/soft-fp.h>
 
 #undef count_leading_zeros
 #define count_leading_zeros  __FP_CLZ