Merge f_field.h into field.h

[openssl.git] / crypto / ec / curve448 / arch_x86_64 / arch_intrinsics.h

diff --git a/crypto/ec/curve448/arch_x86_64/arch_intrinsics.h b/crypto/ec/curve448/arch_x86_64/arch_intrinsics.h
index 9ecaefc73abaae2ae467a4ac4b4dc56d0c57daf8..cca3f81c17ee78f87b7700aade1a722f7ca25077 100644 (file)
--- a/crypto/ec/curve448/arch_x86_64/arch_intrinsics.h
+++ b/crypto/ec/curve448/arch_x86_64/arch_intrinsics.h
@@ -1,7 +1,14 @@
-/* Copyright (c) 2014-2016 Cryptography Research, Inc.
- * Released under the MIT License.  See LICENSE.txt for license information.
+/*
+ * Copyright 2017 The OpenSSL Project Authors. All Rights Reserved.
+ * Copyright 2014-2016 Cryptography Research, Inc.
+ *
+ * Licensed under the OpenSSL license (the "License").  You may not use
+ * this file except in compliance with the License.  You can obtain a copy
+ * in the file LICENSE in the source distribution or at
+ * https://www.openssl.org/source/license.html
+ *
+ * Originally written by Mike Hamburg
  */
-
 #ifndef __ARCH_X86_64_ARCH_INTRINSICS_H__
 #define __ARCH_X86_64_ARCH_INTRINSICS_H__
 
@@ -10,8 +17,10 @@
 #include <openssl/e_os2.h>
 
 /* FUTURE: autogenerate */
-static __inline__ __uint128_t widemul(const uint64_t *a, const uint64_t *b) {
-  uint64_t c,d;
+static __inline__ __uint128_t widemul(const uint64_t *a, const uint64_t *b)
+{
+  uint64_t c, d;
+
   #ifndef __BMI2__
       __asm__ volatile
           ("movq %[a], %%rax;"
@@ -27,11 +36,13 @@ static __inline__ __uint128_t widemul(const uint64_t *a, const uint64_t *b) {
            : [b]"m"(*b), [a]"m"(*a)
            : "rdx");
   #endif
-  return (((__uint128_t)(d))<<64) | c;
+  return (((__uint128_t)(d)) << 64) | c;
 }
 
-static __inline__ __uint128_t widemul_rm(uint64_t a, const uint64_t *b) {
-  uint64_t c,d;
+static __inline__ __uint128_t widemul_rm(uint64_t a, const uint64_t *b)
+{
+  uint64_t c, d;
+
   #ifndef __BMI2__
       __asm__ volatile
           ("movq %[a], %%rax;"
@@ -45,11 +56,13 @@ static __inline__ __uint128_t widemul_rm(uint64_t a, const uint64_t *b) {
            : [c]"=r"(c), [d]"=r"(d)
            : [b]"m"(*b), [a]"d"(a));
   #endif
-  return (((__uint128_t)(d))<<64) | c;
+  return (((__uint128_t)(d)) << 64) | c;
 }
 
-static __inline__ __uint128_t widemul_rr(uint64_t a, uint64_t b) {
-  uint64_t c,d;
+static __inline__ __uint128_t widemul_rr(uint64_t a, uint64_t b)
+{
+  uint64_t c, d;
+
   #ifndef __BMI2__
       __asm__ volatile
           ("mulq %[b];"
@@ -62,11 +75,13 @@ static __inline__ __uint128_t widemul_rr(uint64_t a, uint64_t b) {
            : [c]"=r"(c), [d]"=r"(d)
            : [b]"r"(b), [a]"d"(a));
   #endif
-  return (((__uint128_t)(d))<<64) | c;
+  return (((__uint128_t)(d)) << 64) | c;
 }
 
-static __inline__ __uint128_t widemul2(const uint64_t *a, const uint64_t *b) {
-  uint64_t c,d;
+static __inline__ __uint128_t widemul2(const uint64_t *a, const uint64_t *b)
+{
+  uint64_t c, d;
+
   #ifndef __BMI2__
       __asm__ volatile
           ("movq %[a], %%rax; "
@@ -84,11 +99,13 @@ static __inline__ __uint128_t widemul2(const uint64_t *a, const uint64_t *b) {
            : [b]"m"(*b), [a]"m"(*a)
            : "rdx");
   #endif
-  return (((__uint128_t)(d))<<64) | c;
+  return (((__uint128_t)(d)) << 64) | c;
 }
 
-static __inline__ void mac(__uint128_t *acc, const uint64_t *a, const uint64_t *b) {
-  uint64_t lo = *acc, hi = *acc>>64;
+static __inline__ void mac(__uint128_t *acc, const uint64_t *a,
+                           const uint64_t *b)
+{
+  uint64_t lo = *acc, hi = *acc >> 64;
   
   #ifdef __BMI2__
       uint64_t c,d;
@@ -111,12 +128,14 @@ static __inline__ void mac(__uint128_t *acc, const uint64_t *a, const uint64_t *
            : "rax", "rdx", "cc");
   #endif
   
-  *acc = (((__uint128_t)(hi))<<64) | lo;
+  *acc = (((__uint128_t)(hi)) << 64) | lo;
 }
 
-static __inline__ void macac(__uint128_t *acc, __uint128_t *acc2, const uint64_t *a, const uint64_t *b) {
-  uint64_t lo = *acc, hi = *acc>>64;
-  uint64_t lo2 = *acc2, hi2 = *acc2>>64;
+static __inline__ void macac(__uint128_t *acc, __uint128_t *acc2,
+                             const uint64_t *a, const uint64_t *b)
+{
+  uint64_t lo = *acc, hi = *acc >> 64;
+  uint64_t lo2 = *acc2, hi2 = *acc2 >> 64;
   
   #ifdef __BMI2__
       uint64_t c,d;
@@ -143,12 +162,13 @@ static __inline__ void macac(__uint128_t *acc, __uint128_t *acc2, const uint64_t
            : "rax", "rdx", "cc");
   #endif
   
-  *acc = (((__uint128_t)(hi))<<64) | lo;
-  *acc2 = (((__uint128_t)(hi2))<<64) | lo2;
+  *acc = (((__uint128_t)(hi)) << 64) | lo;
+  *acc2 = (((__uint128_t)(hi2)) << 64) | lo2;
 }
 
-static __inline__ void mac_rm(__uint128_t *acc, uint64_t a, const uint64_t *b) {
-  uint64_t lo = *acc, hi = *acc>>64;
+static __inline__ void mac_rm(__uint128_t *acc, uint64_t a, const uint64_t *b)
+{
+  uint64_t lo = *acc, hi = *acc >> 64;
   
   #ifdef __BMI2__
       uint64_t c,d;
@@ -170,11 +190,12 @@ static __inline__ void mac_rm(__uint128_t *acc, uint64_t a, const uint64_t *b) {
            : "rax", "rdx", "cc");
   #endif
   
-  *acc = (((__uint128_t)(hi))<<64) | lo;
+  *acc = (((__uint128_t)(hi)) << 64) | lo;
 }
 
-static __inline__ void mac_rr(__uint128_t *acc, uint64_t a, const uint64_t b) {
-  uint64_t lo = *acc, hi = *acc>>64;
+static __inline__ void mac_rr(__uint128_t *acc, uint64_t a, const uint64_t b)
+{
+  uint64_t lo = *acc, hi = *acc >> 64;
   
   #ifdef __BMI2__
       uint64_t c,d;
@@ -195,11 +216,13 @@ static __inline__ void mac_rr(__uint128_t *acc, uint64_t a, const uint64_t b) {
            : "rdx", "cc");
   #endif
   
-  *acc = (((__uint128_t)(hi))<<64) | lo;
+  *acc = (((__uint128_t)(hi)) << 64) | lo;
 }
 
-static __inline__ void mac2(__uint128_t *acc, const uint64_t *a, const uint64_t *b) {
-  uint64_t lo = *acc, hi = *acc>>64;
+static __inline__ void mac2(__uint128_t *acc, const uint64_t *a,
+                            const uint64_t *b)
+{
+  uint64_t lo = *acc, hi = *acc >> 64;
   
   #ifdef __BMI2__
       uint64_t c,d;
@@ -224,11 +247,14 @@ static __inline__ void mac2(__uint128_t *acc, const uint64_t *a, const uint64_t
            : "rax", "rdx", "cc");
   #endif
   
-  *acc = (((__uint128_t)(hi))<<64) | lo;
+  *acc = (((__uint128_t)(hi)) << 64) | lo;
 }
 
-static __inline__ void msb(__uint128_t *acc, const uint64_t *a, const uint64_t *b) {
-  uint64_t lo = *acc, hi = *acc>>64;
+static __inline__ void msb(__uint128_t *acc, const uint64_t *a,
+                           const uint64_t *b)
+{
+  uint64_t lo = *acc, hi = *acc >> 64;
+
   #ifdef __BMI2__
       uint64_t c,d;
       __asm__ volatile
@@ -249,11 +275,14 @@ static __inline__ void msb(__uint128_t *acc, const uint64_t *a, const uint64_t *
            : [b]"m"(*b), [a]"m"(*a)
            : "rax", "rdx", "cc");
   #endif
-  *acc = (((__uint128_t)(hi))<<64) | lo;
+  *acc = (((__uint128_t)(hi)) << 64) | lo;
 }
 
-static __inline__ void msb2(__uint128_t *acc, const uint64_t *a, const uint64_t *b) {
-  uint64_t lo = *acc, hi = *acc>>64;
+static __inline__ void msb2(__uint128_t *acc, const uint64_t *a,
+                            const uint64_t *b)
+{
+  uint64_t lo = *acc, hi = *acc >> 64;
+
   #ifdef __BMI2__
       uint64_t c,d;
       __asm__ volatile
@@ -280,8 +309,10 @@ static __inline__ void msb2(__uint128_t *acc, const uint64_t *a, const uint64_t
   
 }
 
-static __inline__ void mrs(__uint128_t *acc, const uint64_t *a, const uint64_t *b) {
-  uint64_t c,d, lo = *acc, hi = *acc>>64;
+static __inline__ void mrs(__uint128_t *acc, const uint64_t *a,
+                           const uint64_t *b)
+{
+  uint64_t c,d, lo = *acc, hi = *acc >> 64;
   __asm__ volatile
       ("movq %[a], %%rdx; "
        "mulx %[b], %[c], %[d]; "
@@ -290,16 +321,18 @@ static __inline__ void mrs(__uint128_t *acc, const uint64_t *a, const uint64_t *
        : [c]"=r"(c), [d]"=r"(d), [lo]"+r"(lo), [hi]"+r"(hi)
        : [b]"m"(*b), [a]"m"(*a)
        : "rdx", "cc");
-  *acc = (((__uint128_t)(d))<<64) | c;
+  *acc = (((__uint128_t)(d)) << 64) | c;
 }
 
-static __inline__ uint64_t word_is_zero(uint64_t x) {
+static __inline__ uint64_t word_is_zero(uint64_t x)
+{
   __asm__ volatile("neg %0; sbb %0, %0;" : "+r"(x));
   return ~x;
 }
 
-static inline uint64_t shrld(__uint128_t x, int n) {
-    return x>>n;
+static inline uint64_t shrld(__uint128_t x, int n)
+{
+    return x >> n;
 }
 
 #endif /* __ARCH_X86_64_ARCH_INTRINSICS_H__ */