Refactor i386 libm code forcing underflow exceptions.

This patch refactors code in sysdeps/i386/fpu that forces underflow
exceptions to use common macros for that purpose as far as possible.
(Although some of the macros end up used in only one place, I think
it's cleanest to define all these macros together so that all the code
forcing underflow uses such macros.  Some more uses of such macros
will also be introduced when fixing remaining bugs about missing
underflow exceptions, and it would be possible to do further
refactoring of the macros in i386-math-asm.h to share more code by
using other macros internally.  Places that test for underflow by
examining the representation of the argument with integer operations,
rather that using floating-point comparisons on the argument or
result, are unchanged by this patch.)

Most of this code uses a macro MO to abstract away the differences
between PIC and non-PIC memory references to constants.  log1p
functions, however, hardcoded PIC conditionals for this.  Because the
common macros rely on the use of MO, I changed the log1p functions to
use the normal style here, and, for consistency, also made that change
to log1pl which is otherwise unaffected by this patch.

Tested for x86.

	* sysdeps/i386/fpu/i386-math-asm.h (DEFINE_LDBL_MIN): New macro.
	(FLT_CHECK_FORCE_UFLOW): Likewise.
	(DBL_CHECK_FORCE_UFLOW): Likewise.
	(FLT_CHECK_FORCE_UFLOW_NARROW): Likewise.
	(DBL_CHECK_FORCE_UFLOW_NARROW): Likewise.
	(LDBL_CHECK_FORCE_UFLOW_NONNEG_NAN): Likewise.
	(FLT_CHECK_FORCE_UFLOW_NONNAN): Likewise.
	(DBL_CHECK_FORCE_UFLOW_NONNAN): Likewise.
	(FLT_CHECK_FORCE_UFLOW_NONNEG): Likewise.
	(DBL_CHECK_FORCE_UFLOW_NONNEG): Likewise.
	(LDBL_CHECK_FORCE_UFLOW_NONNEG): Likewise.
	* sysdeps/i386/fpu/e_asin.S: Include <i386-math-asm.h>.
	(dbl_min): Replace with use of DEFINE_DBL_MIN.
	(__ieee754_asin): Use DBL_CHECK_FORCE_UFLOW.
	* sysdeps/i386/fpu/e_asinf.S: Include <i386-math-asm.h>.
	(flt_min): Replace with use of DEFINE_FLT_MIN.
	(__ieee754_asinf): Use FLT_CHECK_FORCE_UFLOW.
	* sysdeps/i386/fpu/e_atan2.S: Include <i386-math-asm.h>.
	(dbl_min): Replace with use of DEFINE_DBL_MIN.
	(__ieee754_atan2): Use DBL_CHECK_FORCE_UFLOW_NARROW.
	* sysdeps/i386/fpu/e_atan2f.S: Include <i386-math-asm.h>.
	(flt_min): Replace with use of DEFINE_FLT_MIN.
	(__ieee754_atan2f): Use FLT_CHECK_FORCE_UFLOW_NARROW.
	* sysdeps/i386/fpu/e_atanh.S: Include <i386-math-asm.h>.
	(dbl_min): Replace with use of DEFINE_DBL_MIN.
	(__ieee754_atanh): Use DBL_CHECK_FORCE_UFLOW_NONNEG.
	* sysdeps/i386/fpu/e_atanhf.S: Include <i386-math-asm.h>.
	(flt_min): Replace with use of DEFINE_FLT_MIN.
	(__ieee754_atanhf): Use FLT_CHECK_FORCE_UFLOW_NONNEG.
	* sysdeps/i386/fpu/e_exp2l.S: Include <i386-math-asm.h>.
	(ldbl_min): Replace with use of DEFINE_LDBL_MIN.
	(__ieee754_exp2l): Use LDBL_CHECK_FORCE_UFLOW_NONNEG_NAN.
	* sysdeps/i386/fpu/e_expl.S: Include <i386-math-asm.h>.
	[!USE_AS_EXPM1L] (cmin): Replace with use of DEFINE_LDBL_MIN.
	(IEEE754_EXPL): Use LDBL_CHECK_FORCE_UFLOW_NONNEG.
	* sysdeps/i386/fpu/s_atan.S: Include <i386-math-asm.h>.
	(dbl_min): Replace with use of DEFINE_DBL_MIN.
	(__atan): Use DBL_CHECK_FORCE_UFLOW.
	* sysdeps/i386/fpu/s_atanf.S: Include <i386-math-asm.h>.
	(flt_min): Replace with use of DEFINE_FLT_MIN.
	(__atanf): Use FLT_CHECK_FORCE_UFLOW.
	* sysdeps/i386/fpu/s_expm1.S: Include <i386-math-asm.h>.
	(dbl_min): Replace with use of DEFINE_DBL_MIN.
	(__expm1): Use DBL_CHECK_FORCE_UFLOW.  Move underflow check after
	main computation.
	* sysdeps/i386/fpu/s_expm1f.S: Include <i386-math-asm.h>.
	(flt_min): Replace with use of DEFINE_FLT_MIN.
	(__expm1f): Use FLT_CHECK_FORCE_UFLOW.  Move underflow check after
	main computation.
	* sysdeps/i386/fpu/s_log1p.S: Include <i386-math-asm.h>.
	(dbl_min): Replace with use of DEFINE_DBL_MIN.
	(MO): New macro.
	(__log1p): Use MO.  Use DBL_CHECK_FORCE_UFLOW_NONNAN.
	* sysdeps/i386/fpu/s_log1pf.S: Include <i386-math-asm.h>.
	(flt_min): Replace with use of DEFINE_FLT_MIN.
	(MO): New macro.
	(__log1pf): Use MO.  Use FLT_CHECK_FORCE_UFLOW_NONNAN.
	* sysdeps/i386/fpu/s_log1pl.S (MO): New macro.
	(__log1pl): Use MO.

1 files changed, 168 insertions, 0 deletions

diff --git a/sysdeps/i386/fpu/i386-math-asm.h b/sysdeps/i386/fpu/i386-math-asm.h
index c15029d..5d8d847 100644
--- a/sysdeps/i386/fpu/i386-math-asm.h
+++ b/sysdeps/i386/fpu/i386-math-asm.h
@@ -52,6 +52,14 @@ flt_min:					\
 dbl_min:					\
 	.byte 0, 0, 0, 0, 0, 0, 0x10, 0;	\
 	.size dbl_min, .-dbl_min;
+#define DEFINE_LDBL_MIN					\
+	.section .rodata.cst16,"aM",@progbits,16;	\
+	.p2align 4;					\
+	.type ldbl_min,@object;				\
+ldbl_min:						\
+	.byte 0, 0, 0, 0, 0, 0, 0, 0x80, 0x1, 0;	\
+	.byte 0, 0, 0, 0, 0, 0;				\
+	.size ldbl_min, .-ldbl_min;
 
 /* Remove excess range and precision by storing a value on the stack
    and loading it back.  The value is given to be nonnegative or NaN;
@@ -123,4 +131,164 @@ dbl_min:					\
 	addl	$8, %esp;			\
 	cfi_adjust_cfa_offset (-8);
 
+/* Force an underflow exception if the given value is subnormal.  The
+   relevant constant for the minimum of the type must have been
+   defined, the MO macro must have been defined for access to memory
+   operands, and, if PIC, the PIC register must have been loaded.  */
+#define FLT_CHECK_FORCE_UFLOW			\
+	flds	MO(flt_min);			\
+	fld	%st(1);				\
+	fabs;					\
+	fucompp;				\
+	fnstsw;					\
+	sahf;					\
+	jnc 6424f;				\
+	subl	$4, %esp;			\
+	cfi_adjust_cfa_offset (4);		\
+	fld	%st(0);				\
+	fmul	%st(0);				\
+	fstps	(%esp);				\
+	addl	$4, %esp;			\
+	cfi_adjust_cfa_offset (-4);		\
+6424:
+#define DBL_CHECK_FORCE_UFLOW			\
+	fldl	MO(dbl_min);			\
+	fld	%st(1);				\
+	fabs;					\
+	fucompp;				\
+	fnstsw;					\
+	sahf;					\
+	jnc 6453f;				\
+	subl	$8, %esp;			\
+	cfi_adjust_cfa_offset (8);		\
+	fld	%st(0);				\
+	fmul	%st(0);				\
+	fstpl	(%esp);				\
+	addl	$8, %esp;			\
+	cfi_adjust_cfa_offset (-8);		\
+6453:
+
+/* Likewise, but also remove excess range and precision if the value
+   is subnormal.  */
+#define FLT_CHECK_FORCE_UFLOW_NARROW		\
+	flds	MO(flt_min);			\
+	fld	%st(1);				\
+	fabs;					\
+	fucompp;				\
+	fnstsw;					\
+	sahf;					\
+	jnc 6424f;				\
+	subl	$4, %esp;			\
+	cfi_adjust_cfa_offset (4);		\
+	fld	%st(0);				\
+	fmul	%st(0);				\
+	fstps	(%esp);				\
+	fstps	(%esp);				\
+	flds	(%esp);				\
+	addl	$4, %esp;			\
+	cfi_adjust_cfa_offset (-4);		\
+6424:
+#define DBL_CHECK_FORCE_UFLOW_NARROW		\
+	fldl	MO(dbl_min);			\
+	fld	%st(1);				\
+	fabs;					\
+	fucompp;				\
+	fnstsw;					\
+	sahf;					\
+	jnc 6453f;				\
+	subl	$8, %esp;			\
+	cfi_adjust_cfa_offset (8);		\
+	fld	%st(0);				\
+	fmul	%st(0);				\
+	fstpl	(%esp);				\
+	fstpl	(%esp);				\
+	fldl	(%esp);				\
+	addl	$8, %esp;			\
+	cfi_adjust_cfa_offset (-8);		\
+6453:
+
+/* Likewise, but the argument is nonnegative or NaN.  */
+#define LDBL_CHECK_FORCE_UFLOW_NONNEG_NAN	\
+	fldt	MO(ldbl_min);			\
+	fld	%st(1);				\
+	fucompp;				\
+	fnstsw;					\
+	sahf;					\
+	jnc 6464f;				\
+	fld	%st(0);				\
+	fmul	%st(0);				\
+	fstp	%st(0);				\
+6464:
+
+/* Likewise, but the argument is not a NaN.  */
+#define FLT_CHECK_FORCE_UFLOW_NONNAN		\
+	fld %st(0);				\
+	fabs;					\
+	fcomps	MO(flt_min);			\
+	fnstsw;					\
+	sahf;					\
+	jnc 6424f;				\
+	subl	$4, %esp;			\
+	cfi_adjust_cfa_offset (4);		\
+	fld	%st(0);				\
+	fmul	%st(0);				\
+	fstps	(%esp);				\
+	addl	$4, %esp;			\
+	cfi_adjust_cfa_offset (-4);		\
+6424:
+#define DBL_CHECK_FORCE_UFLOW_NONNAN		\
+	fld %st(0);				\
+	fabs;					\
+	fcompl	MO(dbl_min);			\
+	fnstsw;					\
+	sahf;					\
+	jnc 6453f;				\
+	subl	$8, %esp;			\
+	cfi_adjust_cfa_offset (8);		\
+	fld	%st(0);				\
+	fmul	%st(0);				\
+	fstpl	(%esp);				\
+	addl	$8, %esp;			\
+	cfi_adjust_cfa_offset (-8);		\
+6453:
+
+/* Likewise, but the argument is nonnegative and not a NaN.  */
+#define FLT_CHECK_FORCE_UFLOW_NONNEG		\
+	fcoms	MO(flt_min);			\
+	fnstsw;					\
+	sahf;					\
+	jnc 6424f;				\
+	subl	$4, %esp;			\
+	cfi_adjust_cfa_offset (4);		\
+	fld	%st(0);				\
+	fmul	%st(0);				\
+	fstps	(%esp);				\
+	addl	$4, %esp;			\
+	cfi_adjust_cfa_offset (-4);		\
+6424:
+#define DBL_CHECK_FORCE_UFLOW_NONNEG		\
+	fcoml	MO(dbl_min);			\
+	fnstsw;					\
+	sahf;					\
+	jnc 6453f;				\
+	subl	$8, %esp;			\
+	cfi_adjust_cfa_offset (8);		\
+	fld	%st(0);				\
+	fmul	%st(0);				\
+	fstpl	(%esp);				\
+	addl	$8, %esp;			\
+	cfi_adjust_cfa_offset (-8);		\
+6453:
+#define LDBL_CHECK_FORCE_UFLOW_NONNEG		\
+	fldt	MO(ldbl_min);			\
+	fld	%st(1);				\
+	fcompp;					\
+	fnstsw;					\
+	sahf;					\
+	jnc 6464f;				\
+	fld	%st(0);				\
+	fmul	%st(0);				\
+	fstp	%st(0);				\
+6464:
+
 #endif /* i386-math-asm.h.  */