view release on metacpan or  search on metacpan

xs/libgit2/src/sha1.c  view on Meta::CPAN

 * 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(_M_IX86) || defined(_M_X64) || \
	defined(__ppc__) || defined(__ppc64__) || \
	defined(__powerpc__) || defined(__powerpc64__) || \
	defined(__s390__) || defined(__s390x__)

#define get_be32(p)	ntohl(*(const unsigned int *)(p))
#define put_be32(p, v)	do { *(unsigned int *)(p) = htonl(v); } while (0)

#else

#define get_be32(p)	( \
	(*((const unsigned char *)(p) + 0) << 24) | \
	(*((const unsigned char *)(p) + 1) << 16) | \
	(*((const unsigned char *)(p) + 2) << 8) | \
	(*((const 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);