block-sha1: Use '(B&C)+(D&(B^C))' instead of '(B&C)|(D&(B|C))' in round 3

[git.git] / block-sha1 / sha1.c

diff --git a/block-sha1/sha1.c b/block-sha1/sha1.c
index 50b2b42b03f255689b26cc91d7fb02ce5601dff2..5bf1b36bd18882b57c4953a1c9a5aa01d688944f 100644 (file)
--- a/block-sha1/sha1.c
+++ b/block-sha1/sha1.c
@@ -31,7 +31,7 @@ void blk_SHA1_Update(blk_SHA_CTX *ctx, const void *data, unsigned long len)
 {
        int lenW = ctx->lenW;
 
-       ctx->size += len;
+       ctx->size += (unsigned long long) len << 3;
 
        /* Read the data into W and process blocks as they get full
         */
@@ -68,8 +68,8 @@ void blk_SHA1_Final(unsigned char hashout[20], blk_SHA_CTX *ctx)
 
        /* Pad with a binary 1 (ie 0x80), then zeroes, then length
         */
-       padlen[0] = htonl(ctx->size >> (32 - 3));
-       padlen[1] = htonl(ctx->size << 3);
+       padlen[0] = htonl(ctx->size >> 32);
+       padlen[1] = htonl(ctx->size);
 
        blk_SHA1_Update(ctx, pad, 1+ (63 & (55 - ctx->lenW)));
        blk_SHA1_Update(ctx, padlen, 8);
@@ -80,20 +80,45 @@ void blk_SHA1_Final(unsigned char hashout[20], blk_SHA_CTX *ctx)
                ((unsigned int *)hashout)[i] = htonl(ctx->H[i]);
 }
 
-#define SHA_ROT(X,n) (((X) << (n)) | ((X) >> (32-(n))))
+#if defined(__i386__) || defined(__x86_64__)
+
+#define SHA_ASM(op, x, n) ({ unsigned int __res; __asm__(op " %1,%0":"=r" (__res):"i" (n), "0" (x)); __res; })
+#define SHA_ROL(x,n)   SHA_ASM("rol", x, n)
+#define SHA_ROR(x,n)   SHA_ASM("ror", x, n)
+
+#else
+
+#define SHA_ROT(X,l,r) (((X) << (l)) | ((X) >> (r)))
+#define SHA_ROL(X,n)   SHA_ROT(X,n,32-(n))
+#define SHA_ROR(X,n)   SHA_ROT(X,32-(n),n)
+
+#endif
+
+/* This "rolls" over the 512-bit array */
+#define W(x) (array[(x)&15])
+
+/*
+ * Where do we get the source from? The first 16 iterations get it from
+ * the input data, the next mix it from the 512-bit array.
+ */
+#define SHA_SRC(t) htonl(data[t])
+#define SHA_MIX(t) SHA_ROL(W(t+13) ^ W(t+8) ^ W(t+2) ^ W(t), 1)
+
+#define SHA_ROUND(t, input, fn, constant) \
+       TEMP = input(t); W(t) = TEMP; \
+       TEMP += SHA_ROL(A,5) + (fn) + E + (constant); \
+       E = D; D = C; C = SHA_ROR(B, 2); B = A; A = TEMP
+
+#define T_0_15(t)  SHA_ROUND(t, SHA_SRC, (((C^D)&B)^D) , 0x5a827999 )
+#define T_16_19(t) SHA_ROUND(t, SHA_MIX, (((C^D)&B)^D) , 0x5a827999 )
+#define T_20_39(t) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0x6ed9eba1 )
+#define T_40_59(t) SHA_ROUND(t, SHA_MIX, ((B&C)+(D&(B^C))) , 0x8f1bbcdc )
+#define T_60_79(t) SHA_ROUND(t, SHA_MIX, (B^C^D) ,  0xca62c1d6 )
 
 static void blk_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data)
 {
-       int t;
        unsigned int A,B,C,D,E,TEMP;
-       unsigned int W[80];
-
-       for (t = 0; t < 16; t++)
-               W[t] = htonl(data[t]);
-
-       /* Unroll it? */
-       for (t = 16; t <= 79; t++)
-               W[t] = SHA_ROT(W[t-3] ^ W[t-8] ^ W[t-14] ^ W[t-16], 1);
+       unsigned int array[16];
 
        A = ctx->H[0];
        B = ctx->H[1];
@@ -101,37 +126,28 @@ static void blk_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data)
        D = ctx->H[3];
        E = ctx->H[4];
 
-#define T_0_19(t) \
-       TEMP = SHA_ROT(A,5) + (((C^D)&B)^D)     + E + W[t] + 0x5a827999; \
-       E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
+       /* Round 1 - iterations 0-16 take their input from 'data' */
+       T_0_15( 0); T_0_15( 1); T_0_15( 2); T_0_15( 3); T_0_15( 4);
+       T_0_15( 5); T_0_15( 6); T_0_15( 7); T_0_15( 8); T_0_15( 9);
+       T_0_15(10); T_0_15(11); T_0_15(12); T_0_15(13); T_0_15(14);
+       T_0_15(15);
 
-       T_0_19( 0); T_0_19( 1); T_0_19( 2); T_0_19( 3); T_0_19( 4);
-       T_0_19( 5); T_0_19( 6); T_0_19( 7); T_0_19( 8); T_0_19( 9);
-       T_0_19(10); T_0_19(11); T_0_19(12); T_0_19(13); T_0_19(14);
-       T_0_19(15); T_0_19(16); T_0_19(17); T_0_19(18); T_0_19(19);
-
-#define T_20_39(t) \
-       TEMP = SHA_ROT(A,5) + (B^C^D)           + E + W[t] + 0x6ed9eba1; \
-       E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
+       /* Round 1 - tail. Input from 512-bit mixing array */
+       T_16_19(16); T_16_19(17); T_16_19(18); T_16_19(19);
 
+       /* Round 2 */
        T_20_39(20); T_20_39(21); T_20_39(22); T_20_39(23); T_20_39(24);
        T_20_39(25); T_20_39(26); T_20_39(27); T_20_39(28); T_20_39(29);
        T_20_39(30); T_20_39(31); T_20_39(32); T_20_39(33); T_20_39(34);
        T_20_39(35); T_20_39(36); T_20_39(37); T_20_39(38); T_20_39(39);
 
-#define T_40_59(t) \
-       TEMP = SHA_ROT(A,5) + ((B&C)|(D&(B|C))) + E + W[t] + 0x8f1bbcdc; \
-       E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
-
+       /* Round 3 */
        T_40_59(40); T_40_59(41); T_40_59(42); T_40_59(43); T_40_59(44);
        T_40_59(45); T_40_59(46); T_40_59(47); T_40_59(48); T_40_59(49);
        T_40_59(50); T_40_59(51); T_40_59(52); T_40_59(53); T_40_59(54);
        T_40_59(55); T_40_59(56); T_40_59(57); T_40_59(58); T_40_59(59);
 
-#define T_60_79(t) \
-       TEMP = SHA_ROT(A,5) + (B^C^D)           + E + W[t] + 0xca62c1d6; \
-       E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
-
+       /* Round 4 */
        T_60_79(60); T_60_79(61); T_60_79(62); T_60_79(63); T_60_79(64);
        T_60_79(65); T_60_79(66); T_60_79(67); T_60_79(68); T_60_79(69);
        T_60_79(70); T_60_79(71); T_60_79(72); T_60_79(73); T_60_79(74);