/*
- * Based on the Mozilla SHA1 (see mozilla-sha1/sha1.c),
- * optimized to do word accesses rather than byte accesses,
+ * SHA1 routine optimized to do word accesses rather than byte accesses,
* and to avoid unnecessary copies into the context array.
+ *
+ * This was initially based on the Mozilla SHA1 implementation, although
+ * none of the original Mozilla code remains.
*/
-#include <string.h>
-#include <arpa/inet.h>
+/* this is only to get definitions for memcpy(), ntohl() and htonl() */
+#include "../git-compat-util.h"
#include "sha1.h"
-/* Hash one 64-byte block of data */
-static void blk_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data);
+#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
+
+/*
+ * Force usage of rol or ror by selecting 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.
+ */
+
+#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
+
+/*
+ * If you have 32 registers or more, the compiler can (and should)
+ * try to change the array[] accesses into registers. However, on
+ * machines with less than ~25 registers, that won't really work,
+ * and at least gcc will make an unholy mess of it.
+ *
+ * So to avoid that mess which just slows things down, we force
+ * the stores to memory to actually happen (we might be better off
+ * with a 'W(t)=(val);asm("":"+m" (W(t))' there instead, as
+ * suggested by Artur Skawina - that will also make gcc unable to
+ * try to do the silly "optimize away loads" part because it won't
+ * see what the value will be).
+ *
+ * Ben Herrenschmidt reports that on PPC, the C version comes close
+ * to the optimized asm with this (ie on PPC you don't want that
+ * 'volatile', since there are lots of registers).
+ *
+ * On ARM we get the best code generation by forcing a full memory barrier
+ * between each SHA_ROUND, otherwise gcc happily get wild with spilling and
+ * the stack frame size simply explode and performance goes down the drain.
+ */
+
+#if defined(__i386__) || defined(__x86_64__)
+ #define setW(x, val) (*(volatile unsigned int *)&W(x) = (val))
+#elif defined(__GNUC__) && defined(__arm__)
+ #define setW(x, val) do { W(x) = (val); __asm__("":::"memory"); } while (0)
+#else
+ #define setW(x, val) (W(x) = (val))
+#endif
+
+/*
+ * Performance might be improved if the CPU architecture is OK with
+ * unaligned 32-bit loads and a fast ntohl() is available.
+ * Otherwise fall back to byte loads and shifts which is portable,
+ * and is faster on architectures with memory alignment issues.
+ */
+
+#if defined(__i386__) || defined(__x86_64__) || \
+ defined(__ppc__) || defined(__ppc64__) || \
+ defined(__powerpc__) || defined(__powerpc64__) || \
+ defined(__s390__) || defined(__s390x__)
+
+#define get_be32(p) ntohl(*(unsigned int *)(p))
+#define put_be32(p, v) do { *(unsigned int *)(p) = htonl(v); } while (0)
+
+#else
+
+#define get_be32(p) ( \
+ (*((unsigned char *)(p) + 0) << 24) | \
+ (*((unsigned char *)(p) + 1) << 16) | \
+ (*((unsigned char *)(p) + 2) << 8) | \
+ (*((unsigned char *)(p) + 3) << 0) )
+#define put_be32(p, v) do { \
+ unsigned int __v = (v); \
+ *((unsigned char *)(p) + 0) = __v >> 24; \
+ *((unsigned char *)(p) + 1) = __v >> 16; \
+ *((unsigned char *)(p) + 2) = __v >> 8; \
+ *((unsigned char *)(p) + 3) = __v >> 0; } while (0)
+
+#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) get_be32(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, A, B, C, D, E) do { \
+ unsigned int TEMP = input(t); setW(t, TEMP); \
+ E += TEMP + SHA_ROL(A,5) + (fn) + (constant); \
+ B = SHA_ROR(B, 2); } while (0)
+
+#define T_0_15(t, A, B, C, D, E) SHA_ROUND(t, SHA_SRC, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
+#define T_16_19(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
+#define T_20_39(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0x6ed9eba1, A, B, C, D, E )
+#define T_40_59(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, ((B&C)+(D&(B^C))) , 0x8f1bbcdc, A, B, C, D, E )
+#define T_60_79(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0xca62c1d6, A, B, C, D, E )
+
+static void blk_SHA1_Block(blk_SHA_CTX *ctx, const unsigned int *data)
+{
+ unsigned int A,B,C,D,E;
+ unsigned int array[16];
+
+ A = ctx->H[0];
+ B = ctx->H[1];
+ C = ctx->H[2];
+ D = ctx->H[3];
+ E = ctx->H[4];
+
+ /* Round 1 - iterations 0-16 take their input from 'data' */
+ T_0_15( 0, A, B, C, D, E);
+ T_0_15( 1, E, A, B, C, D);
+ T_0_15( 2, D, E, A, B, C);
+ T_0_15( 3, C, D, E, A, B);
+ T_0_15( 4, B, C, D, E, A);
+ T_0_15( 5, A, B, C, D, E);
+ T_0_15( 6, E, A, B, C, D);
+ T_0_15( 7, D, E, A, B, C);
+ T_0_15( 8, C, D, E, A, B);
+ T_0_15( 9, B, C, D, E, A);
+ T_0_15(10, A, B, C, D, E);
+ T_0_15(11, E, A, B, C, D);
+ T_0_15(12, D, E, A, B, C);
+ T_0_15(13, C, D, E, A, B);
+ T_0_15(14, B, C, D, E, A);
+ T_0_15(15, A, B, C, D, E);
+
+ /* Round 1 - tail. Input from 512-bit mixing array */
+ T_16_19(16, E, A, B, C, D);
+ T_16_19(17, D, E, A, B, C);
+ T_16_19(18, C, D, E, A, B);
+ T_16_19(19, B, C, D, E, A);
+
+ /* Round 2 */
+ T_20_39(20, A, B, C, D, E);
+ T_20_39(21, E, A, B, C, D);
+ T_20_39(22, D, E, A, B, C);
+ T_20_39(23, C, D, E, A, B);
+ T_20_39(24, B, C, D, E, A);
+ T_20_39(25, A, B, C, D, E);
+ T_20_39(26, E, A, B, C, D);
+ T_20_39(27, D, E, A, B, C);
+ T_20_39(28, C, D, E, A, B);
+ T_20_39(29, B, C, D, E, A);
+ T_20_39(30, A, B, C, D, E);
+ T_20_39(31, E, A, B, C, D);
+ T_20_39(32, D, E, A, B, C);
+ T_20_39(33, C, D, E, A, B);
+ T_20_39(34, B, C, D, E, A);
+ T_20_39(35, A, B, C, D, E);
+ T_20_39(36, E, A, B, C, D);
+ T_20_39(37, D, E, A, B, C);
+ T_20_39(38, C, D, E, A, B);
+ T_20_39(39, B, C, D, E, A);
+
+ /* Round 3 */
+ T_40_59(40, A, B, C, D, E);
+ T_40_59(41, E, A, B, C, D);
+ T_40_59(42, D, E, A, B, C);
+ T_40_59(43, C, D, E, A, B);
+ T_40_59(44, B, C, D, E, A);
+ T_40_59(45, A, B, C, D, E);
+ T_40_59(46, E, A, B, C, D);
+ T_40_59(47, D, E, A, B, C);
+ T_40_59(48, C, D, E, A, B);
+ T_40_59(49, B, C, D, E, A);
+ T_40_59(50, A, B, C, D, E);
+ T_40_59(51, E, A, B, C, D);
+ T_40_59(52, D, E, A, B, C);
+ T_40_59(53, C, D, E, A, B);
+ T_40_59(54, B, C, D, E, A);
+ T_40_59(55, A, B, C, D, E);
+ T_40_59(56, E, A, B, C, D);
+ T_40_59(57, D, E, A, B, C);
+ T_40_59(58, C, D, E, A, B);
+ T_40_59(59, B, C, D, E, A);
+
+ /* Round 4 */
+ T_60_79(60, A, B, C, D, E);
+ T_60_79(61, E, A, B, C, D);
+ T_60_79(62, D, E, A, B, C);
+ T_60_79(63, C, D, E, A, B);
+ T_60_79(64, B, C, D, E, A);
+ T_60_79(65, A, B, C, D, E);
+ T_60_79(66, E, A, B, C, D);
+ T_60_79(67, D, E, A, B, C);
+ T_60_79(68, C, D, E, A, B);
+ T_60_79(69, B, C, D, E, A);
+ T_60_79(70, A, B, C, D, E);
+ T_60_79(71, E, A, B, C, D);
+ T_60_79(72, D, E, A, B, C);
+ T_60_79(73, C, D, E, A, B);
+ T_60_79(74, B, C, D, E, A);
+ T_60_79(75, A, B, C, D, E);
+ T_60_79(76, E, A, B, C, D);
+ T_60_79(77, D, E, A, B, C);
+ T_60_79(78, C, D, E, A, B);
+ T_60_79(79, B, C, D, E, A);
+
+ ctx->H[0] += A;
+ ctx->H[1] += B;
+ ctx->H[2] += C;
+ ctx->H[3] += D;
+ ctx->H[4] += E;
+}
void blk_SHA1_Init(blk_SHA_CTX *ctx)
{
- ctx->lenW = 0;
ctx->size = 0;
- /* Initialize H with the magic constants (see FIPS180 for constants)
- */
+ /* Initialize H with the magic constants (see FIPS180 for constants) */
ctx->H[0] = 0x67452301;
ctx->H[1] = 0xefcdab89;
ctx->H[2] = 0x98badcfe;
ctx->H[4] = 0xc3d2e1f0;
}
-
void blk_SHA1_Update(blk_SHA_CTX *ctx, const void *data, unsigned long len)
{
- int lenW = ctx->lenW;
+ int lenW = ctx->size & 63;
- ctx->size += (unsigned long long) len << 3;
+ ctx->size += len;
- /* Read the data into W and process blocks as they get full
- */
+ /* Read the data into W and process blocks as they get full */
if (lenW) {
int left = 64 - lenW;
if (len < left)
memcpy(lenW + (char *)ctx->W, data, left);
lenW = (lenW + left) & 63;
len -= left;
- data += left;
- ctx->lenW = lenW;
+ data = ((const char *)data + left);
if (lenW)
return;
- blk_SHA1Block(ctx, ctx->W);
+ blk_SHA1_Block(ctx, ctx->W);
}
while (len >= 64) {
- blk_SHA1Block(ctx, data);
- data += 64;
+ blk_SHA1_Block(ctx, data);
+ data = ((const char *)data + 64);
len -= 64;
}
- if (len) {
+ if (len)
memcpy(ctx->W, data, len);
- ctx->lenW = len;
- }
}
-
void blk_SHA1_Final(unsigned char hashout[20], blk_SHA_CTX *ctx)
{
static const unsigned char pad[64] = { 0x80 };
unsigned int padlen[2];
int i;
- /* Pad with a binary 1 (ie 0x80), then zeroes, then length
- */
- padlen[0] = htonl(ctx->size >> 32);
- padlen[1] = htonl(ctx->size);
+ /* Pad with a binary 1 (ie 0x80), then zeroes, then length */
+ padlen[0] = htonl(ctx->size >> 29);
+ padlen[1] = htonl(ctx->size << 3);
- blk_SHA1_Update(ctx, pad, 1+ (63 & (55 - ctx->lenW)));
+ i = ctx->size & 63;
+ blk_SHA1_Update(ctx, pad, 1+ (63 & (55 - i)));
blk_SHA1_Update(ctx, padlen, 8);
- /* Output hash
- */
+ /* Output hash */
for (i = 0; i < 5; i++)
- ((unsigned int *)hashout)[i] = htonl(ctx->H[i]);
-}
-
-#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)
-{
- 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_ROL(W[t-3] ^ W[t-8] ^ W[t-14] ^ W[t-16], 1);
-
- A = ctx->H[0];
- B = ctx->H[1];
- C = ctx->H[2];
- D = ctx->H[3];
- E = ctx->H[4];
-
-#define T_0_19(t) \
- 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_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_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_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);
- T_60_79(70); T_60_79(71); T_60_79(72); T_60_79(73); T_60_79(74);
- T_60_79(75); T_60_79(76); T_60_79(77); T_60_79(78); T_60_79(79);
-
- ctx->H[0] += A;
- ctx->H[1] += B;
- ctx->H[2] += C;
- ctx->H[3] += D;
- ctx->H[4] += E;
+ put_be32(hashout + i*4, ctx->H[i]);
}