/*
- * 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__))
-void blk_SHA1_Init(blk_SHA_CTX *ctx)
-{
- ctx->size = 0;
-
- /* Initialize H with the magic constants (see FIPS180 for constants)
- */
- ctx->H[0] = 0x67452301;
- ctx->H[1] = 0xefcdab89;
- ctx->H[2] = 0x98badcfe;
- ctx->H[3] = 0x10325476;
- ctx->H[4] = 0xc3d2e1f0;
-}
-
-
-void blk_SHA1_Update(blk_SHA_CTX *ctx, const void *data, unsigned long len)
-{
- int lenW = ctx->size & 63;
+/*
+ * 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.
+ */
- ctx->size += len;
+#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)
- /* Read the data into W and process blocks as they get full
- */
- if (lenW) {
- int left = 64 - lenW;
- if (len < left)
- left = len;
- memcpy(lenW + (char *)ctx->W, data, left);
- lenW = (lenW + left) & 63;
- len -= left;
- data += left;
- if (lenW)
- return;
- blk_SHA1Block(ctx, ctx->W);
- }
- while (len >= 64) {
- blk_SHA1Block(ctx, data);
- data += 64;
- len -= 64;
- }
- if (len)
- memcpy(ctx->W, data, len);
-}
+#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)
-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;
+#endif
- /* Pad with a binary 1 (ie 0x80), then zeroes, then length
- */
- padlen[0] = htonl(ctx->size >> 29);
- padlen[1] = htonl(ctx->size << 3);
+/*
+ * 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.
+ */
- i = ctx->size & 63;
- blk_SHA1_Update(ctx, pad, 1+ (63 & (55 - i)));
- blk_SHA1_Update(ctx, padlen, 8);
+#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
- /* Output hash
- */
- for (i = 0; i < 5; i++)
- ((unsigned int *)hashout)[i] = htonl(ctx->H[i]);
-}
+/*
+ * 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__)
+#if defined(__i386__) || defined(__x86_64__) || \
+ defined(__ppc__) || defined(__ppc64__) || \
+ defined(__powerpc__) || defined(__powerpc64__) || \
+ defined(__s390__) || defined(__s390x__)
-#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)
+#define get_be32(p) ntohl(*(unsigned int *)(p))
+#define put_be32(p, v) do { *(unsigned int *)(p) = htonl(v); } while (0)
#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)
+#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
* 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 { \
- unsigned int TEMP = input(t); W(t) = TEMP; \
- TEMP += E + SHA_ROL(A,5) + (fn) + (constant); \
- B = SHA_ROR(B, 2); E = TEMP; } while (0)
+ 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_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_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data)
+static void blk_SHA1_Block(blk_SHA_CTX *ctx, const unsigned int *data)
{
unsigned int A,B,C,D,E;
unsigned int array[16];
ctx->H[3] += D;
ctx->H[4] += E;
}
+
+void blk_SHA1_Init(blk_SHA_CTX *ctx)
+{
+ ctx->size = 0;
+
+ /* Initialize H with the magic constants (see FIPS180 for constants) */
+ ctx->H[0] = 0x67452301;
+ ctx->H[1] = 0xefcdab89;
+ ctx->H[2] = 0x98badcfe;
+ ctx->H[3] = 0x10325476;
+ ctx->H[4] = 0xc3d2e1f0;
+}
+
+void blk_SHA1_Update(blk_SHA_CTX *ctx, const void *data, unsigned long len)
+{
+ 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;
+ if (len < left)
+ left = len;
+ memcpy(lenW + (char *)ctx->W, data, left);
+ lenW = (lenW + left) & 63;
+ len -= left;
+ data = ((const char *)data + left);
+ if (lenW)
+ return;
+ blk_SHA1_Block(ctx, ctx->W);
+ }
+ while (len >= 64) {
+ blk_SHA1_Block(ctx, data);
+ data = ((const char *)data + 64);
+ len -= 64;
+ }
+ if (len)
+ memcpy(ctx->W, data, 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 >> 29);
+ padlen[1] = htonl(ctx->size << 3);
+
+ i = ctx->size & 63;
+ blk_SHA1_Update(ctx, pad, 1+ (63 & (55 - i)));
+ blk_SHA1_Update(ctx, padlen, 8);
+
+ /* Output hash */
+ for (i = 0; i < 5; i++)
+ put_be32(hashout + i*4, ctx->H[i]);
+}