Add missing long double functions to Cygwin

This patch adds the long double functions missing in newlib to Cygwin.
Apart from some self-written additions (exp10l, finite{f,l}, isinf{f,l},
isnan{f,l}, pow10l) the files are taken from the Mingw-w64 math lib.
Minor changes were required, e.g. substitue _WIN64 with __x86_64__ and
fixing __FLT_RPT_DOMAIN/__FLT_RPT_ERANGE for Cygwin.

Cygwin:
	* math: New subdir with math functions.
	* Makefile.in (VPATH): Add math subdir.
	(MATH_OFILES): List of object files collected from building files in
	math subdir.
	(DLL_OFILES): Add $(MATH_OFILES).
	${CURDIR}/libm.a: Add $(MATH_OFILES) to build.
	* common.din: Add new functions from math subdir.
	* i686.din: Align to new math subdir.  Remove functions now commonly
	available.
	* x86_64.din: Ditto.
	* math.h: math.h wrapper to define mingw structs used in some files in
	math subdir.
	* include/cygwin/version.h: Bump API minor version.

newlib:
	* libc/include/complex.h: Add prototypes for complex long double
	functions.  Only define for Cygwin.
	* libc/include/math.h: Additionally enable prototypes of long double
	functions for Cygwin.  Add Cygwin-only prototypes for dreml, sincosl,
	exp10l and pow10l.  Explain why we don't add them to newlib.
	* libc/include/tgmath.h: Enable long double handling on Cygwin.

Signed-off-by: Corinna Vinschen <corinna@vinschen.de>

1 files changed, 120 insertions, 0 deletions

diff --git a/winsup/cygwin/math/ceilf.S b/winsup/cygwin/math/ceilf.S
new file mode 100644
index 000000000..605c7bffa
--- /dev/null
+++ b/winsup/cygwin/math/ceilf.S
@@ -0,0 +1,120 @@
+/**
+ * This file has no copyright assigned and is placed in the Public Domain.
+ * This file is part of the mingw-w64 runtime package.
+ * No warranty is given; refer to the file DISCLAIMER.PD within this package.
+ */
+#include <_mingw_mac.h>
+
+	.file	"ceilf.S"
+	.text
+	.align 4
+	.globl __MINGW_USYMBOL(ceilf)
+	.def	__MINGW_USYMBOL(ceilf);	.scl	2;	.type	32;	.endef
+#ifdef __x86_64__
+	.seh_proc	__MINGW_USYMBOL(ceilf)
+#endif
+
+__MINGW_USYMBOL(ceilf):
+#if defined(_AMD64_) || defined(__x86_64__)
+        subq    $24, %rsp
+        .seh_stackalloc 24
+        .seh_endprologue
+        movd    %xmm0, 12(%rsp)
+        movl    12(%rsp), %eax
+        movl    %eax, %ecx
+        movl    %eax, %edx
+        sarl    $23, %ecx
+        andl    $255, %ecx
+        subl    $127, %ecx
+        cmpl    $22, %ecx
+        jg      .l4
+        testl   %ecx, %ecx
+        js      .l5
+        movl    $8388607, %r8d
+        sarl    %cl, %r8d
+        testl   %eax, %r8d
+        je      .l3
+        addss   .hugeval(%rip), %xmm0
+        ucomiss .zeroval(%rip), %xmm0
+        jbe     .l2
+        testl   %eax, %eax
+        jle     .l1
+        movl    $8388608, %eax
+        sarl    %cl, %eax
+        addl    %eax, %edx
+.l1:
+        movl    %r8d, %eax
+        notl    %eax
+        andl    %edx, %eax
+.l2:
+        movl    %eax, 8(%rsp)
+        movss   8(%rsp), %xmm0
+.l3:
+        addq    $24, %rsp
+        ret
+        .p2align 4,,10
+.l4:
+        addl    $-128, %ecx
+        jne     .l3
+        addss   %xmm0, %xmm0
+        addq    $24, %rsp
+        ret
+        .p2align 4,,10
+.l5:
+        addss   .hugeval(%rip), %xmm0
+        ucomiss .zeroval(%rip), %xmm0
+        jbe     .islesseqzero
+        testl   %eax, %eax
+        js      .l6
+        movl    $1065353216, %edx
+        cmovne  %edx, %eax
+.islesseqzero:
+        movl    %eax, 8(%rsp)
+        movss   8(%rsp), %xmm0
+        addq    $24, %rsp
+        ret
+        .p2align 4,,10
+.l6:
+        movl    $-2147483648, 8(%rsp)
+        movss   8(%rsp), %xmm0
+        addq    $24, %rsp
+        ret
+        .seh_endproc
+        .section .rdata,"dr"
+        .align 4
+.hugeval:
+        .long   1900671690
+        .align 4
+.zeroval:
+        .long   0
+#elif defined(_ARM_) || defined(__arm__)
+	vmrs	r1, fpscr
+	bic		r0, r1, #0x00c00000
+	orr		r0, r0, #0x00400000 /* Round towards Plus Infinity */
+	vmsr	fpscr, r0
+	vcvt.s32.f32	s0, s0
+	vcvt.f32.s32	s0, s0
+	vmsr	fpscr, r1
+	bx	lr
+#elif defined(_X86_) || defined(__i386__)
+	flds	4(%esp)
+	subl	$8,%esp
+
+	fstcw	4(%esp)			/* store fpu control word */
+
+	/* We use here %edx although only the low 1 bits are defined.
+	   But none of the operations should care and they are faster
+	   than the 16 bit operations.  */
+	movl	$0x0800,%edx		/* round towards +oo */
+	orl	4(%esp),%edx
+	andl	$0xfbff,%edx
+	movl	%edx,(%esp)
+	fldcw	(%esp)			/* load modified control word */
+
+	frndint				/* round */
+
+	fldcw	4(%esp)			/* restore original control word */
+
+	addl	$8,%esp
+	ret
+#endif