slow-hash: fix for big endian

src/crypto/slow-hash.c

@@ -109,8 +109,8 @@ extern void aesb_pseudo_round(const uint8_t *in, uint8_t *out, const uint8_t *ex
     memcpy(b + AES_BLOCK_SIZE, state.hs.b + 64, AES_BLOCK_SIZE); \
     xor64(b + AES_BLOCK_SIZE, state.hs.b + 80); \
     xor64(b + AES_BLOCK_SIZE + 8, state.hs.b + 88); \
-    division_result = state.hs.w[12]; \
-    sqrt_result = state.hs.w[13]; \
+    division_result = SWAP64LE(state.hs.w[12]); \
+    sqrt_result = SWAP64LE(state.hs.w[13]); \
   } while (0)
 
 #define VARIANT2_SHUFFLE_ADD_SSE2(base_ptr, offset) \
@@ -145,30 +145,31 @@ extern void aesb_pseudo_round(const uint8_t *in, uint8_t *out, const uint8_t *ex
     const uint64_t chunk1_old[2] = { chunk1[0], chunk1[1] }; \
     \
     uint64_t b1[2]; \
-    memcpy(b1, b + 16, 16); \
-    chunk1[0] = chunk3[0] + b1[0]; \
-    chunk1[1] = chunk3[1] + b1[1]; \
+    memcpy_swap64le(b1, b + 16, 2); \
+    chunk1[0] = SWAP64LE(chunk3[0] + b1[0]); \
+    chunk1[1] = SWAP64LE(chunk3[1] + b1[1]); \
     \
     uint64_t a0[2]; \
-    memcpy(a0, a, 16); \
-    chunk3[0] = chunk2[0] + a0[0]; \
-    chunk3[1] = chunk2[1] + a0[1]; \
+    memcpy_swap64le(a0, a, 2); \
+    chunk3[0] = SWAP64LE(chunk2[0] + a0[0]); \
+    chunk3[1] = SWAP64LE(chunk2[1] + a0[1]); \
     \
     uint64_t b0[2]; \
-    memcpy(b0, b, 16); \
-    chunk2[0] = chunk1_old[0] + b0[0]; \
-    chunk2[1] = chunk1_old[1] + b0[1]; \
+    memcpy_swap64le(b0, b, 2); \
+    chunk2[0] = SWAP64LE(chunk1_old[0] + b0[0]); \
+    chunk2[1] = SWAP64LE(chunk1_old[1] + b0[1]); \
   } while (0)
 
 #define VARIANT2_INTEGER_MATH_DIVISION_STEP(b, ptr) \
-  ((uint64_t*)(b))[0] ^= division_result ^ (sqrt_result << 32); \
+  uint64_t tmpx = division_result ^ (sqrt_result << 32); \
+  ((uint64_t*)(b))[0] ^= SWAP64LE(tmpx); \
   { \
-    const uint64_t dividend = ((uint64_t*)(ptr))[1]; \
-    const uint32_t divisor = (((uint64_t*)(ptr))[0] + (uint32_t)(sqrt_result << 1)) | 0x80000001UL; \
+    const uint64_t dividend = SWAP64LE(((uint64_t*)(ptr))[1]); \
+    const uint32_t divisor = (SWAP64LE(((uint64_t*)(ptr))[0]) + (uint32_t)(sqrt_result << 1)) | 0x80000001UL; \
     division_result = ((uint32_t)(dividend / divisor)) + \
                      (((uint64_t)(dividend % divisor)) << 32); \
   } \
-  const uint64_t sqrt_input = ((uint64_t*)(ptr))[0] + division_result
+  const uint64_t sqrt_input = SWAP64LE(((uint64_t*)(ptr))[0]) + division_result
 
 #define VARIANT2_INTEGER_MATH_SSE2(b, ptr) \
   do if (variant >= 2) \
@@ -207,10 +208,10 @@ extern void aesb_pseudo_round(const uint8_t *in, uint8_t *out, const uint8_t *ex
 #define VARIANT2_2() \
   do if (variant >= 2) \
   { \
-    *U64(hp_state + (j ^ 0x10)) ^= hi; \
-    *(U64(hp_state + (j ^ 0x10)) + 1) ^= lo; \
-    hi ^= *U64(hp_state + (j ^ 0x20)); \
-    lo ^= *(U64(hp_state + (j ^ 0x20)) + 1); \
+    *U64(hp_state + (j ^ 0x10)) ^= SWAP64LE(hi); \
+    *(U64(hp_state + (j ^ 0x10)) + 1) ^= SWAP64LE(lo); \
+    hi ^= SWAP64LE(*U64(hp_state + (j ^ 0x20))); \
+    lo ^= SWAP64LE(*(U64(hp_state + (j ^ 0x20)) + 1)); \
   } while (0)
 
 
@@ -1408,7 +1409,7 @@ static void (*const extra_hashes[4])(const void *, size_t, char *) = {
   hash_extra_blake, hash_extra_groestl, hash_extra_jh, hash_extra_skein
 };
 
-static size_t e2i(const uint8_t* a, size_t count) { return (*((uint64_t*)a) / AES_BLOCK_SIZE) & (count - 1); }
+static size_t e2i(const uint8_t* a, size_t count) { return (SWAP64LE(*((uint64_t*)a)) / AES_BLOCK_SIZE) & (count - 1); }
 
 static void mul(const uint8_t* a, const uint8_t* b, uint8_t* res) {
   uint64_t a0, b0;