Merge pull request #4258 from pks-t/pks/sha1dc-update

SHA1DC update
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 3fb8ae2..354ae3e 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -296,6 +296,9 @@
 # Specify sha1 implementation
 IF (USE_SHA1DC)
 	ADD_DEFINITIONS(-DGIT_SHA1_COLLISIONDETECT)
+	ADD_DEFINITIONS(-DSHA1DC_NO_STANDARD_INCLUDES=1)
+	ADD_DEFINITIONS(-DSHA1DC_CUSTOM_INCLUDE_SHA1_C=\"common.h\")
+	ADD_DEFINITIONS(-DSHA1DC_CUSTOM_INCLUDE_UBC_CHECK_C=\"common.h\")
 	FILE(GLOB SRC_SHA1 src/hash/hash_collisiondetect.c src/hash/sha1dc/*)
 ELSEIF (WIN32 AND NOT MINGW)
 	ADD_DEFINITIONS(-DGIT_SHA1_WIN32)
diff --git a/src/hash/sha1dc/sha1.c b/src/hash/sha1dc/sha1.c
index 8d12b83..facea1b 100644
--- a/src/hash/sha1dc/sha1.c
+++ b/src/hash/sha1dc/sha1.c
@@ -5,31 +5,75 @@
 * https://opensource.org/licenses/MIT
 ***/
 
+#ifndef SHA1DC_NO_STANDARD_INCLUDES
 #include <string.h>
 #include <memory.h>
 #include <stdio.h>
 #include <stdlib.h>
+#endif
+
+#ifdef SHA1DC_CUSTOM_INCLUDE_SHA1_C
+#include SHA1DC_CUSTOM_INCLUDE_SHA1_C
+#endif
+
+#ifndef SHA1DC_INIT_SAFE_HASH_DEFAULT
+#define SHA1DC_INIT_SAFE_HASH_DEFAULT 1
+#endif
 
 #include "sha1.h"
 #include "ubc_check.h"
 
 
-/* 
+/*
    Because Little-Endian architectures are most common,
-   we only set BIGENDIAN if one of these conditions is met.
+   we only set SHA1DC_BIGENDIAN if one of these conditions is met.
    Note that all MSFT platforms are little endian,
    so none of these will be defined under the MSC compiler.
    If you are compiling on a big endian platform and your compiler does not define one of these,
    you will have to add whatever macros your tool chain defines to indicate Big-Endianness.
  */
-#if (defined(__BYTE_ORDER) && (__BYTE_ORDER == __BIG_ENDIAN)) || \
-    (defined(__BYTE_ORDER__) && (__BYTE_ORDER__ == __BIG_ENDIAN__)) || \
-    defined(__BIG_ENDIAN__) || defined(__ARMEB__) || defined(__THUMBEB__) ||  defined(__AARCH64EB__) || \
-    defined(_MIPSEB) || defined(__MIPSEB) || defined(__MIPSEB__)
+#ifdef SHA1DC_BIGENDIAN
+#undef SHA1DC_BIGENDIAN
+#endif
 
-#define BIGENDIAN	(1)
+#if (defined(_BYTE_ORDER) || defined(__BYTE_ORDER) || defined(__BYTE_ORDER__))
 
-#endif /*ENDIANNESS SELECTION*/
+#if ((defined(_BYTE_ORDER) && (_BYTE_ORDER == _BIG_ENDIAN)) || \
+     (defined(__BYTE_ORDER) && (__BYTE_ORDER == __BIG_ENDIAN)) || \
+     (defined(__BYTE_ORDER__) && (__BYTE_ORDER__ == __BIG_ENDIAN__)) )
+#define SHA1DC_BIGENDIAN
+#endif
+
+#else
+
+#if (defined(_BIG_ENDIAN) || defined(__BIG_ENDIAN) || defined(__BIG_ENDIAN__) || \
+     defined(__ARMEB__) || defined(__THUMBEB__) || defined(__AARCH64EB__) || \
+     defined(__MIPSEB__) || defined(__MIPSEB) || defined(_MIPSEB) || \
+     defined(__sparc))
+#define SHA1DC_BIGENDIAN
+#endif
+
+#endif
+
+#if (defined(SHA1DC_FORCE_LITTLEENDIAN) && defined(SHA1DC_BIGENDIAN))
+#undef SHA1DC_BIGENDIAN
+#endif
+#if (defined(SHA1DC_FORCE_BIGENDIAN) && !defined(SHA1DC_BIGENDIAN))
+#define SHA1DC_BIGENDIAN
+#endif
+/*ENDIANNESS SELECTION*/
+
+#if (defined SHA1DC_FORCE_UNALIGNED_ACCESS || \
+     defined(__amd64__) || defined(__amd64) || defined(__x86_64__) || defined(__x86_64) || \
+     defined(i386) || defined(__i386) || defined(__i386__) || defined(__i486__)  || \
+     defined(__i586__) || defined(__i686__) || defined(_M_IX86) || defined(__X86__) || \
+     defined(_X86_) || defined(__THW_INTEL__) || defined(__I86__) || defined(__INTEL__) || \
+     defined(__386) || defined(_M_X64) || defined(_M_AMD64))
+
+#define SHA1DC_ALLOW_UNALIGNED_ACCESS
+
+#endif /*UNALIGNMENT DETECTION*/
+
 
 #define rotate_right(x,n) (((x)>>(n))|((x)<<(32-(n))))
 #define rotate_left(x,n)  (((x)<<(n))|((x)>>(32-(n))))
@@ -39,11 +83,11 @@
 
 #define sha1_mix(W, t)  (rotate_left(W[t - 3] ^ W[t - 8] ^ W[t - 14] ^ W[t - 16], 1))
 
-#if defined(BIGENDIAN)
+#ifdef SHA1DC_BIGENDIAN
 	#define sha1_load(m, t, temp)  { temp = m[t]; }
 #else
 	#define sha1_load(m, t, temp)  { temp = m[t]; sha1_bswap32(temp); }
-#endif /*define(BIGENDIAN)*/
+#endif
 
 #define sha1_store(W, t, x)	*(volatile uint32_t *)&W[t] = x
 
@@ -872,6 +916,11 @@
 	ihvout[0] = ihvin[0] + a; ihvout[1] = ihvin[1] + b; ihvout[2] = ihvin[2] + c; ihvout[3] = ihvin[3] + d; ihvout[4] = ihvin[4] + e; \
 }
 
+#ifdef _MSC_VER
+#pragma warning(push)
+#pragma warning(disable: 4127)  /* Complier complains about the checks in the above macro being constant. */
+#endif
+
 #ifdef DOSTORESTATE0
 SHA1_RECOMPRESS(0)
 #endif
@@ -1192,6 +1241,10 @@
 SHA1_RECOMPRESS(79)
 #endif
 
+#ifdef _MSC_VER
+#pragma warning(pop)
+#endif
+
 static void sha1_recompression_step(uint32_t step, uint32_t ihvin[5], uint32_t ihvout[5], const uint32_t me2[80], const uint32_t state[5])
 {
 	switch (step)
@@ -1609,7 +1662,7 @@
 	unsigned i, j;
 	uint32_t ubc_dv_mask[DVMASKSIZE] = { 0xFFFFFFFF };
 	uint32_t ihvtmp[5];
-	
+
 	ctx->ihv1[0] = ctx->ihv[0];
 	ctx->ihv1[1] = ctx->ihv[1];
 	ctx->ihv1[2] = ctx->ihv[2];
@@ -1665,7 +1718,7 @@
 	ctx->ihv[3] = 0x10325476;
 	ctx->ihv[4] = 0xC3D2E1F0;
 	ctx->found_collision = 0;
-	ctx->safe_hash = 1;
+	ctx->safe_hash = SHA1DC_INIT_SAFE_HASH_DEFAULT;
 	ctx->ubc_check = 1;
 	ctx->detect_coll = 1;
 	ctx->reduced_round_coll = 0;
@@ -1713,6 +1766,7 @@
 void SHA1DCUpdate(SHA1_CTX* ctx, const char* buf, size_t len)
 {
 	unsigned left, fill;
+
 	if (len == 0)
 		return;
 
@@ -1731,7 +1785,13 @@
 	while (len >= 64)
 	{
 		ctx->total += 64;
+
+#if defined(SHA1DC_ALLOW_UNALIGNED_ACCESS)
 		sha1_process(ctx, (uint32_t*)(buf));
+#else
+		memcpy(ctx->buffer, buf, 64);
+		sha1_process(ctx, (uint32_t*)(ctx->buffer));
+#endif /* defined(SHA1DC_ALLOW_UNALIGNED_ACCESS) */
 		buf += 64;
 		len -= 64;
 	}
@@ -1790,3 +1850,7 @@
 	output[19] = (unsigned char)(ctx->ihv[4]);
 	return ctx->found_collision;
 }
+
+#ifdef SHA1DC_CUSTOM_TRAILING_INCLUDE_SHA1_C
+#include SHA1DC_CUSTOM_TRAILING_INCLUDE_SHA1_C
+#endif
diff --git a/src/hash/sha1dc/sha1.h b/src/hash/sha1dc/sha1.h
index e867724..1e4e94b 100644
--- a/src/hash/sha1dc/sha1.h
+++ b/src/hash/sha1dc/sha1.h
@@ -5,42 +5,37 @@
 * https://opensource.org/licenses/MIT
 ***/
 
+#ifndef SHA1DC_SHA1_H
+#define SHA1DC_SHA1_H
+
 #if defined(__cplusplus)
 extern "C" {
 #endif
 
+#ifndef SHA1DC_NO_STANDARD_INCLUDES
 #include <stdint.h>
+#endif
 
-/* uses SHA-1 message expansion to expand the first 16 words of W[] to 80 words */
-/* void sha1_message_expansion(uint32_t W[80]); */
-
-/* sha-1 compression function; first version takes a message block pre-parsed as 16 32-bit integers, second version takes an already expanded message) */
-/* void sha1_compression(uint32_t ihv[5], const uint32_t m[16]);
-void sha1_compression_W(uint32_t ihv[5], const uint32_t W[80]); */
-
-/* same as sha1_compression_W, but additionally store intermediate states */
+/* sha-1 compression function that takes an already expanded message, and additionally store intermediate states */
 /* only stores states ii (the state between step ii-1 and step ii) when DOSTORESTATEii is defined in ubc_check.h */
 void sha1_compression_states(uint32_t[5], const uint32_t[16], uint32_t[80], uint32_t[80][5]);
 
 /*
-// function type for sha1_recompression_step_T (uint32_t ihvin[5], uint32_t ihvout[5], const uint32_t me2[80], const uint32_t state[5])
-// where 0 <= T < 80
-//       me2 is an expanded message (the expansion of an original message block XOR'ed with a disturbance vector's message block difference)
-//       state is the internal state (a,b,c,d,e) before step T of the SHA-1 compression function while processing the original message block
-// the function will return:
-//       ihvin: the reconstructed input chaining value
-//       ihvout: the reconstructed output chaining value
+// Function type for sha1_recompression_step_T (uint32_t ihvin[5], uint32_t ihvout[5], const uint32_t me2[80], const uint32_t state[5]).
+// Where 0 <= T < 80
+//       me2 is an expanded message (the expansion of an original message block XOR'ed with a disturbance vector's message block difference.)
+//       state is the internal state (a,b,c,d,e) before step T of the SHA-1 compression function while processing the original message block.
+// The function will return:
+//       ihvin: The reconstructed input chaining value.
+//       ihvout: The reconstructed output chaining value.
 */
 typedef void(*sha1_recompression_type)(uint32_t*, uint32_t*, const uint32_t*, const uint32_t*);
 
-/* table of sha1_recompression_step_0, ... , sha1_recompression_step_79 */
-/* extern sha1_recompression_type sha1_recompression_step[80];*/
-
-/* a callback function type that can be set to be called when a collision block has been found: */
+/* A callback function type that can be set to be called when a collision block has been found: */
 /* void collision_block_callback(uint64_t byteoffset, const uint32_t ihvin1[5], const uint32_t ihvin2[5], const uint32_t m1[80], const uint32_t m2[80]) */
 typedef void(*collision_block_callback)(uint64_t, const uint32_t*, const uint32_t*, const uint32_t*, const uint32_t*);
 
-/* the SHA-1 context */
+/* The SHA-1 context. */
 typedef struct {
 	uint64_t total;
 	uint32_t ihv[5];
@@ -59,30 +54,34 @@
 	uint32_t states[80][5];
 } SHA1_CTX;
 
-/* initialize SHA-1 context */
+/* Initialize SHA-1 context. */
 void SHA1DCInit(SHA1_CTX*);
 
 /*
-// function to enable safe SHA-1 hashing:
-// collision attacks are thwarted by hashing a detected near-collision block 3 times
-// think of it as extending SHA-1 from 80-steps to 240-steps for such blocks:
-//   the best collision attacks against SHA-1 have complexity about 2^60,
-//   thus for 240-steps an immediate lower-bound for the best cryptanalytic attacks would 2^180
-//   an attacker would be better off using a generic birthday search of complexity 2^80
-//
-// enabling safe SHA-1 hashing will result in the correct SHA-1 hash for messages where no collision attack was detected
-// but it will result in a different SHA-1 hash for messages where a collision attack was detected
-// this will automatically invalidate SHA-1 based digital signature forgeries
-// enabled by default
+    Function to enable safe SHA-1 hashing:
+    Collision attacks are thwarted by hashing a detected near-collision block 3 times.
+    Think of it as extending SHA-1 from 80-steps to 240-steps for such blocks:
+        The best collision attacks against SHA-1 have complexity about 2^60,
+        thus for 240-steps an immediate lower-bound for the best cryptanalytic attacks would be 2^180.
+        An attacker would be better off using a generic birthday search of complexity 2^80.
+
+   Enabling safe SHA-1 hashing will result in the correct SHA-1 hash for messages where no collision attack was detected,
+   but it will result in a different SHA-1 hash for messages where a collision attack was detected.
+   This will automatically invalidate SHA-1 based digital signature forgeries.
+   Enabled by default.
 */
 void SHA1DCSetSafeHash(SHA1_CTX*, int);
 
-/* function to disable or enable the use of Unavoidable Bitconditions (provides a significant speed up) */
-/* enabled by default */
+/*
+    Function to disable or enable the use of Unavoidable Bitconditions (provides a significant speed up).
+    Enabled by default
+ */
 void SHA1DCSetUseUBC(SHA1_CTX*, int);
 
-/* function to disable or enable the use of Collision Detection */
-/* enabled by default */
+/*
+    Function to disable or enable the use of Collision Detection.
+    Enabled by default.
+ */
 void SHA1DCSetUseDetectColl(SHA1_CTX*, int);
 
 /* function to disable or enable the detection of reduced-round SHA-1 collisions */
@@ -98,8 +97,14 @@
 
 /* obtain SHA-1 hash from SHA-1 context */
 /* returns: 0 = no collision detected, otherwise = collision found => warn user for active attack */
-int  SHA1DCFinal(unsigned char[20], SHA1_CTX*); 
+int  SHA1DCFinal(unsigned char[20], SHA1_CTX*);
 
 #if defined(__cplusplus)
 }
 #endif
+
+#ifdef SHA1DC_CUSTOM_TRAILING_INCLUDE_SHA1_H
+#include SHA1DC_CUSTOM_TRAILING_INCLUDE_SHA1_H
+#endif
+
+#endif
diff --git a/src/hash/sha1dc/ubc_check.c b/src/hash/sha1dc/ubc_check.c
index 27d0976..b3beff2 100644
--- a/src/hash/sha1dc/ubc_check.c
+++ b/src/hash/sha1dc/ubc_check.c
@@ -24,7 +24,12 @@
 // ubc_check has been verified against ubc_check_verify using the 'ubc_check_test' program in the tools section
 */
 
+#ifndef SHA1DC_NO_STANDARD_INCLUDES
 #include <stdint.h>
+#endif
+#ifdef SHA1DC_CUSTOM_INCLUDE_UBC_CHECK_C
+#include SHA1DC_CUSTOM_INCLUDE_UBC_CHECK_C
+#endif
 #include "ubc_check.h"
 
 static const uint32_t DV_I_43_0_bit 	= (uint32_t)(1) << 0;
@@ -361,3 +366,7 @@
 
 	dvmask[0]=mask;
 }
+
+#ifdef SHA1DC_CUSTOM_TRAILING_INCLUDE_UBC_CHECK_C
+#include SHA1DC_CUSTOM_TRAILING_INCLUDE_UBC_CHECK_C
+#endif
diff --git a/src/hash/sha1dc/ubc_check.h b/src/hash/sha1dc/ubc_check.h
index b349bed..d7e17dc 100644
--- a/src/hash/sha1dc/ubc_check.h
+++ b/src/hash/sha1dc/ubc_check.h
@@ -20,14 +20,16 @@
 // thus one needs to do the recompression check for each DV that has its bit set
 */
 
-#ifndef UBC_CHECK_H
-#define UBC_CHECK_H
+#ifndef SHA1DC_UBC_CHECK_H
+#define SHA1DC_UBC_CHECK_H
 
 #if defined(__cplusplus)
 extern "C" {
 #endif
 
+#ifndef SHA1DC_NO_STANDARD_INCLUDES
 #include <stdint.h>
+#endif
 
 #define DVMASKSIZE 1
 typedef struct { int dvType; int dvK; int dvB; int testt; int maski; int maskb; uint32_t dm[80]; } dv_info_t;
@@ -43,4 +45,8 @@
 }
 #endif
 
-#endif /* UBC_CHECK_H */
+#ifdef SHA1DC_CUSTOM_TRAILING_INCLUDE_UBC_CHECK_H
+#include SHA1DC_CUSTOM_TRAILING_INCLUDE_UBC_CHECK_H
+#endif
+
+#endif