Fix pow missing underflows (bug 18825).

Similar to various other bugs in this area, pow functions can fail to
raise the underflow exception when the result is tiny and inexact but
one or more low bits of the intermediate result that is scaled down
(or, in the i386 case, converted from a wider evaluation format) are
zero.  This patch forces the exception in a similar way to previous
fixes, thereby concluding the fixes for known bugs with missing
underflow exceptions currently filed in Bugzilla.

Tested for x86_64, x86, mips64 and powerpc.

	[BZ #18825]
	* sysdeps/i386/fpu/i386-math-asm.h (FLT_NARROW_EVAL_UFLOW_NONNAN):
	New macro.
	(DBL_NARROW_EVAL_UFLOW_NONNAN): Likewise.
	(LDBL_CHECK_FORCE_UFLOW_NONNAN): Likewise.
	* sysdeps/i386/fpu/e_pow.S: Use DEFINE_DBL_MIN.
	(__ieee754_pow): Use DBL_NARROW_EVAL_UFLOW_NONNAN instead of
	DBL_NARROW_EVAL, reloading the PIC register as needed.
	* sysdeps/i386/fpu/e_powf.S: Use DEFINE_FLT_MIN.
	(__ieee754_powf): Use FLT_NARROW_EVAL_UFLOW_NONNAN instead of
	FLT_NARROW_EVAL.  Use separate return path for case when first
	argument is NaN.
	* sysdeps/i386/fpu/e_powl.S: Include <i386-math-asm.h>.  Use
	DEFINE_LDBL_MIN.
	(__ieee754_powl): Use LDBL_CHECK_FORCE_UFLOW_NONNAN, reloading the
	PIC register.
	* sysdeps/ieee754/dbl-64/e_pow.c (__ieee754_pow): Use
	math_check_force_underflow_nonneg.
	* sysdeps/ieee754/flt-32/e_powf.c (__ieee754_powf): Force
	underflow for subnormal result.
	* sysdeps/ieee754/ldbl-128/e_powl.c (__ieee754_powl): Likewise.
	* sysdeps/ieee754/ldbl-128ibm/e_powl.c (__ieee754_powl): Use
	math_check_force_underflow_nonneg.
	* sysdeps/x86/fpu/powl_helper.c (__powl_helper): Use
	math_check_force_underflow.
	* sysdeps/x86_64/fpu/x86_64-math-asm.h
	(LDBL_CHECK_FORCE_UFLOW_NONNAN): New macro.
	* sysdeps/x86_64/fpu/e_powl.S: Include <x86_64-math-asm.h>.  Use
	DEFINE_LDBL_MIN.
	(__ieee754_powl): Use LDBL_CHECK_FORCE_UFLOW_NONNAN.
	* math/auto-libm-test-in: Add more tests of pow.
	* math/auto-libm-test-out: Regenerated.

1 files changed, 46 insertions, 0 deletions

diff --git a/sysdeps/i386/fpu/i386-math-asm.h b/sysdeps/i386/fpu/i386-math-asm.h
index 5d8d847cc3..4bac3bf5ab 100644
--- a/sysdeps/i386/fpu/i386-math-asm.h
+++ b/sysdeps/i386/fpu/i386-math-asm.h
@@ -131,6 +131,40 @@ ldbl_min:						\
 	addl	$8, %esp;			\
 	cfi_adjust_cfa_offset (-8);
 
+/* Likewise, but the non-NaN argument may be negative.  */
+#define FLT_NARROW_EVAL_UFLOW_NONNAN		\
+	subl	$4, %esp;			\
+	cfi_adjust_cfa_offset (4);		\
+	fld	%st(0);				\
+	fabs;					\
+	fcomps	MO(flt_min);			\
+	fnstsw;					\
+	sahf;					\
+	jnc 6424f;				\
+	fld	%st(0);				\
+	fmul	%st(0);				\
+	fstps	(%esp);				\
+6424:	fstps	(%esp);				\
+	flds	(%esp);				\
+	addl	$4, %esp;			\
+	cfi_adjust_cfa_offset (-4);
+#define DBL_NARROW_EVAL_UFLOW_NONNAN		\
+	subl	$8, %esp;			\
+	cfi_adjust_cfa_offset (8);		\
+	fld	%st(0);				\
+	fabs;					\
+	fcompl	MO(dbl_min);			\
+	fnstsw;					\
+	sahf;					\
+	jnc 6453f;				\
+	fld	%st(0);				\
+	fmul	%st(0);				\
+	fstpl	(%esp);				\
+6453:	fstpl	(%esp);				\
+	fldl	(%esp);				\
+	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
@@ -251,6 +285,18 @@ ldbl_min:						\
 	addl	$8, %esp;			\
 	cfi_adjust_cfa_offset (-8);		\
 6453:
+#define LDBL_CHECK_FORCE_UFLOW_NONNAN		\
+	fldt	MO(ldbl_min);			\
+	fld	%st(1);				\
+	fabs;					\
+	fcompp;					\
+	fnstsw;					\
+	sahf;					\
+	jnc 6464f;				\
+	fld	%st(0);				\
+	fmul	%st(0);				\
+	fstp	%st(0);				\
+6464:
 
 /* Likewise, but the argument is nonnegative and not a NaN.  */
 #define FLT_CHECK_FORCE_UFLOW_NONNEG		\