x86_64-gf2m.pl: add missing Windows build fix for #2963.

[openssl.git] / crypto / bn / asm / x86_64-gcc.c

diff --git a/crypto/bn/asm/x86_64-gcc.c b/crypto/bn/asm/x86_64-gcc.c
index c4d941d0b4c7f1b36d59935abcd432f44d49f1d8..dfb7506267c41e31ebba74983ad5521c652c89bf 100644 (file)
--- a/crypto/bn/asm/x86_64-gcc.c
+++ b/crypto/bn/asm/x86_64-gcc.c
@@ -1,4 +1,5 @@
-#ifdef __SUNPRO_C
+#include "../bn_lcl.h"
+#if !(defined(__GNUC__) && __GNUC__>=2)
 # include "../bn_asm.c"        /* kind of dirty hack for Sun Studio */
 #else
 /*
@@ -54,7 +55,14 @@
  *    machine.
  */
 
+#if defined(_WIN64) || !defined(__LP64__)
+#define BN_ULONG unsigned long long
+#else
 #define BN_ULONG unsigned long
+#endif
+
+#undef mul
+#undef mul_add
 
 /*
  * "m"(a), "+m"(r)     is the way to favor DirectPath µ-code;
@@ -90,14 +98,14 @@
                : "cc");                \
        (r)=carry, carry=high;          \
        } while (0)
-
+#undef sqr
 #define sqr(r0,r1,a)                   \
        asm ("mulq %2"                  \
                : "=a"(r0),"=d"(r1)     \
                : "a"(a)                \
                : "cc");
 
-BN_ULONG bn_mul_add_words(BN_ULONG *rp, BN_ULONG *ap, int num, BN_ULONG w)
+BN_ULONG bn_mul_add_words(BN_ULONG *rp, const BN_ULONG *ap, int num, BN_ULONG w)
        {
        BN_ULONG c1=0;
 
@@ -121,7 +129,7 @@ BN_ULONG bn_mul_add_words(BN_ULONG *rp, BN_ULONG *ap, int num, BN_ULONG w)
        return(c1);
        } 
 
-BN_ULONG bn_mul_words(BN_ULONG *rp, BN_ULONG *ap, int num, BN_ULONG w)
+BN_ULONG bn_mul_words(BN_ULONG *rp, const BN_ULONG *ap, int num, BN_ULONG w)
        {
        BN_ULONG c1=0;
 
@@ -144,7 +152,7 @@ BN_ULONG bn_mul_words(BN_ULONG *rp, BN_ULONG *ap, int num, BN_ULONG w)
        return(c1);
        } 
 
-void bn_sqr_words(BN_ULONG *r, BN_ULONG *a, int n)
+void bn_sqr_words(BN_ULONG *r, const BN_ULONG *a, int n)
         {
        if (n <= 0) return;
 
@@ -175,21 +183,23 @@ BN_ULONG bn_div_words(BN_ULONG h, BN_ULONG l, BN_ULONG d)
        return ret;
 }
 
-BN_ULONG bn_add_words (BN_ULONG *rp, BN_ULONG *ap, BN_ULONG *bp,int n)
-{ BN_ULONG ret=0,i=0;
+BN_ULONG bn_add_words (BN_ULONG *rp, const BN_ULONG *ap, const BN_ULONG *bp,int n)
+{ BN_ULONG ret;
+  size_t i=0;
 
        if (n <= 0) return 0;
 
        asm (
-       "       subq    %2,%2           \n"
+       "       subq    %0,%0           \n"     /* clear carry */
+       "       jmp     1f              \n"
        ".p2align 4                     \n"
        "1:     movq    (%4,%2,8),%0    \n"
        "       adcq    (%5,%2,8),%0    \n"
        "       movq    %0,(%3,%2,8)    \n"
-       "       leaq    1(%2),%2        \n"
+       "       lea     1(%2),%2        \n"
        "       loop    1b              \n"
        "       sbbq    %0,%0           \n"
-               : "=&a"(ret),"+c"(n),"=&r"(i)
+               : "=&r"(ret),"+c"(n),"+r"(i)
                : "r"(rp),"r"(ap),"r"(bp)
                : "cc"
        );
@@ -198,21 +208,23 @@ BN_ULONG bn_add_words (BN_ULONG *rp, BN_ULONG *ap, BN_ULONG *bp,int n)
 }
 
 #ifndef SIMICS
-BN_ULONG bn_sub_words (BN_ULONG *rp, BN_ULONG *ap, BN_ULONG *bp,int n)
-{ BN_ULONG ret=0,i=0;
+BN_ULONG bn_sub_words (BN_ULONG *rp, const BN_ULONG *ap, const BN_ULONG *bp,int n)
+{ BN_ULONG ret;
+  size_t i=0;
 
        if (n <= 0) return 0;
 
        asm (
-       "       subq    %2,%2           \n"
+       "       subq    %0,%0           \n"     /* clear borrow */
+       "       jmp     1f              \n"
        ".p2align 4                     \n"
        "1:     movq    (%4,%2,8),%0    \n"
        "       sbbq    (%5,%2,8),%0    \n"
        "       movq    %0,(%3,%2,8)    \n"
-       "       leaq    1(%2),%2        \n"
+       "       lea     1(%2),%2        \n"
        "       loop    1b              \n"
        "       sbbq    %0,%0           \n"
-               : "=&a"(ret),"+c"(n),"=&r"(i)
+               : "=&r"(ret),"+c"(n),"+r"(i)
                : "r"(rp),"r"(ap),"r"(bp)
                : "cc"
        );
@@ -485,7 +497,7 @@ void bn_mul_comba4(BN_ULONG *r, BN_ULONG *a, BN_ULONG *b)
        r[7]=c2;
        }
 
-void bn_sqr_comba8(BN_ULONG *r, BN_ULONG *a)
+void bn_sqr_comba8(BN_ULONG *r, const BN_ULONG *a)
        {
        BN_ULONG t1,t2;
        BN_ULONG c1,c2,c3;
@@ -561,7 +573,7 @@ void bn_sqr_comba8(BN_ULONG *r, BN_ULONG *a)
        r[15]=c1;
        }
 
-void bn_sqr_comba4(BN_ULONG *r, BN_ULONG *a)
+void bn_sqr_comba4(BN_ULONG *r, const BN_ULONG *a)
        {
        BN_ULONG t1,t2;
        BN_ULONG c1,c2,c3;