block-sha1: try to use rol/ror appropriately

Use the one with the smaller constant.  It _can_ generate slightly
smaller code (a constant of 1 is special), but perhaps more importantly
it's possibly faster on any uarch that does a rotate with a loop.

Signed-off-by: Linus Torvalds <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: torvalds

block-sha1/sha1.c

@@ -80,7 +80,19 @@ 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,n)	(((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
 
 static void blk_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data)
 {
@@ -93,7 +105,7 @@ static void blk_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data)
 
 	/* 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);
+		W[t] = SHA_ROL(W[t-3] ^ W[t-8] ^ W[t-14] ^ W[t-16], 1);
 
 	A = ctx->H[0];
 	B = ctx->H[1];
@@ -102,35 +114,35 @@ static void blk_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data)
 	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;
+	TEMP = SHA_ROL(A,5) + (((C^D)&B)^D)     + E + W[t] + 0x5a827999; \
+	E = D; D = C; C = SHA_ROR(B, 2); B = A; A = TEMP;
 
 	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;
+	TEMP = SHA_ROL(A,5) + (B^C^D)           + E + W[t] + 0x6ed9eba1; \
+	E = D; D = C; C = SHA_ROR(B, 2); B = A; A = TEMP;
 
 	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;
+	TEMP = SHA_ROL(A,5) + ((B&C)|(D&(B|C))) + E + W[t] + 0x8f1bbcdc; \
+	E = D; D = C; C = SHA_ROR(B, 2); B = A; A = TEMP;
 
 	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;
+	TEMP = SHA_ROL(A,5) + (B^C^D)           + E + W[t] + 0xca62c1d6; \
+	E = D; D = C; C = SHA_ROR(B, 2); B = A; A = TEMP;
 
 	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);