/*
- * 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"
-#if defined(__i386__) || defined(__x86_64__)
+#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
/*
* Force usage of rol or ror by selecting the one with the smaller constant.
#if defined(__i386__) || defined(__x86_64__)
#define setW(x, val) (*(volatile unsigned int *)&W(x) = (val))
-#elif defined(__arm__)
+#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(_M_IX86) || defined(_M_X64) || \
+ 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) htonl(data[t])
+#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 { \
void blk_SHA1_Update(blk_SHA_CTX *ctx, const void *data, unsigned long len)
{
- int lenW = ctx->size & 63;
+ unsigned int lenW = ctx->size & 63;
ctx->size += len;
/* Read the data into W and process blocks as they get full */
if (lenW) {
- int left = 64 - lenW;
+ unsigned int left = 64 - lenW;
if (len < left)
left = len;
memcpy(lenW + (char *)ctx->W, data, left);
lenW = (lenW + left) & 63;
len -= left;
- data += left;
+ data = ((const char *)data + left);
if (lenW)
return;
blk_SHA1_Block(ctx, ctx->W);
}
while (len >= 64) {
blk_SHA1_Block(ctx, data);
- data += 64;
+ data = ((const char *)data + 64);
len -= 64;
}
if (len)
int i;
/* Pad with a binary 1 (ie 0x80), then zeroes, then length */
- padlen[0] = htonl(ctx->size >> 29);
- padlen[1] = htonl(ctx->size << 3);
+ padlen[0] = htonl((uint32_t)(ctx->size >> 29));
+ padlen[1] = htonl((uint32_t)(ctx->size << 3));
i = ctx->size & 63;
blk_SHA1_Update(ctx, pad, 1+ (63 & (55 - i)));
/* Output hash */
for (i = 0; i < 5; i++)
- ((unsigned int *)hashout)[i] = htonl(ctx->H[i]);
+ put_be32(hashout + i*4, ctx->H[i]);
}