block-sha1: macroize the rounds a bit further

Avoid repeating the shared parts of the different rounds by adding a
macro layer or two. It was already more cpp than C.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

block-sha1/sha1.c

@@ -94,6 +94,27 @@ void blk_SHA1_Final(unsigned char hashout[20], blk_SHA_CTX *ctx)
 
 #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)
 {
 	unsigned int A,B,C,D,E,TEMP;
@@ -105,53 +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_15(t) \
-	TEMP = htonl(data[t]); array[t] = TEMP; \
-	TEMP += SHA_ROL(A,5) + (((C^D)&B)^D) + E + 0x5a827999; \
-	E = D; D = C; C = SHA_ROR(B, 2); 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);
 
-/* This "rolls" over the 512-bit array */
-#define W(x) (array[(x)&15])
-#define SHA_XOR(t) \
-	TEMP = SHA_ROL(W(t+13) ^ W(t+8) ^ W(t+2) ^ W(t), 1); W(t) = TEMP;
-
-#define T_16_19(t) \
-	SHA_XOR(t); \
-	TEMP += SHA_ROL(A,5) + (((C^D)&B)^D) + E + 0x5a827999; \
-	E = D; D = C; C = SHA_ROR(B, 2); 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);
 
-#define T_20_39(t) \
-	SHA_XOR(t); \
-	TEMP += SHA_ROL(A,5) + (B^C^D) + E + 0x6ed9eba1; \
-	E = D; D = C; C = SHA_ROR(B, 2); B = A; A = TEMP;
-
+	/* 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) \
-	SHA_XOR(t); \
-	TEMP += SHA_ROL(A,5) + ((B&C)|(D&(B|C))) + E + 0x8f1bbcdc; \
-	E = D; D = C; C = SHA_ROR(B, 2); 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) \
-	SHA_XOR(t); \
-	TEMP += SHA_ROL(A,5) + (B^C^D) + E + 0xca62c1d6; \
-	E = D; D = C; C = SHA_ROR(B, 2); 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);