summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Makefile29
-rw-r--r--git.git-authors2
-rw-r--r--src/block-sha1/sha1.c280
-rw-r--r--src/block-sha1/sha1.h22
-rw-r--r--src/bswap.h50
-rw-r--r--src/common.h1
-rw-r--r--src/hash.c28
-rw-r--r--src/ppc/sha1.c72
-rw-r--r--src/ppc/sha1.h25
-rw-r--r--src/ppc/sha1ppc.S224
-rw-r--r--src/sha1.h10
-rw-r--r--src/sha1/sha1.c170
-rw-r--r--src/sha1/sha1.h64
13 files changed, 713 insertions, 264 deletions
diff --git a/Makefile b/Makefile
index ad7cf03cc..00c5bdc46 100644
--- a/Makefile
+++ b/Makefile
@@ -3,10 +3,6 @@ all::
# Define NO_VISIBILITY if your compiler does not support symbol
# visibility in general (and the -fvisibility switch in particular).
#
-# Define NO_OPENSSL if you do not have OpenSSL, or if you simply want
-# to use the bundled (Mozilla) SHA1 routines. (The bundled SHA1
-# routines are reported to be faster than OpenSSL on some platforms)
-#
DOXYGEN = doxygen
INSTALL = install
@@ -28,6 +24,7 @@ OS = unix
EXTRA_SRC =
EXTRA_OBJ =
+EXTRA_CFLAGS =
AR_OUT=
CC_OUT=-o # add a space
@@ -60,7 +57,7 @@ endif
SRC_C = $(wildcard src/*.c)
OS_SRC = $(wildcard src/$(OS)/*.c)
SRC_C += $(OS_SRC)
-OBJS = $(patsubst %.c,%.o,$(SRC_C))
+OBJS = $(patsubst %.c,%.o,$(SRC_C)) $(EXTRA_OBJ)
HDRS = $(wildcard src/*.h)
PUBLIC_HEADERS = $(wildcard src/git/*.h)
HDRS += $(PUBLIC_HEADERS)
@@ -73,22 +70,21 @@ TEST_EXE = $(patsubst %.o,%.exe,$(TEST_OBJ))
TEST_RUN = $(patsubst %.exe,%.run,$(TEST_EXE))
TEST_VAL = $(patsubst %.exe,%.val,$(TEST_EXE))
-ifndef NO_OPENSSL
- SHA1_HEADER = <openssl/sha.h>
+ifdef PPC_SHA1
+ EXTRA_SRC += src/ppc/sha1.c src/ppc/sha1ppc.S
+ EXTRA_OBJ += src/ppc/sha1.o src/ppc/sha1ppc.o
+ EXTRA_CFLAGS += -DPPC_SHA1
else
- SHA1_HEADER = "sha1/sha1.h"
- EXTRA_SRC += src/sha1/sha1.c
- EXTRA_OBJ += src/sha1/sha1.o
+ EXTRA_SRC += src/block-sha1/sha1.c
+ EXTRA_OBJ += src/block-sha1/sha1.o
endif
-BASIC_CFLAGS := -Isrc -DSHA1_HEADER='$(SHA1_HEADER)'
+BASIC_CFLAGS := -Isrc
ifndef NO_VISIBILITY
BASIC_CFLAGS += -fvisibility=hidden
endif
-ALL_CFLAGS = $(CFLAGS) $(BASIC_CFLAGS)
-SRC_C += $(EXTRA_SRC)
-OBJ += $(EXTRA_OBJ)
+ALL_CFLAGS = $(CFLAGS) $(BASIC_CFLAGS) $(EXTRA_CFLAGS)
all:: $(GIT_LIB)
@@ -96,7 +92,7 @@ clean:
rm -f $(GIT_LIB)
rm -f libgit2.pc
rm -f *.pdb
- rm -f src/*.o src/sha1/*.o src/unix/*.o src/win32/*.o
+ rm -f src/*.o src/*/*.o
rm -rf apidocs
rm -f *~ src/*~ src/git/*~ src/sha1/*~ src/unix/*~ src/win32/*~
@$(MAKE) -C tests -s --no-print-directory clean
@@ -143,6 +139,9 @@ uninstall:
.c.o:
$(CC) $(ALL_CFLAGS) -c $< $(CC_OUT)$@
+.S.o:
+ $(CC) $(ALL_CFLAGS) -c $< $(CC_OUT)$@
+
$(OBJS): $(HDRS)
$(GIT_LIB): $(OBJS)
rm -f $(GIT_LIB)
diff --git a/git.git-authors b/git.git-authors
index 458c271d8..086ab3e18 100644
--- a/git.git-authors
+++ b/git.git-authors
@@ -38,7 +38,7 @@
# (Paul Kocher is the author of the mozilla-sha1 implementation
# but has otherwise not contributed to git.)
#
-ok Simpkins <adam@adamsimpkins.net> (http transport)
+ok Adam Simpkins <adam@adamsimpkins.net> (http transport)
ok Andreas Ericsson <ae@op5.se>
ok Boyd Lynn Gerber <gerberb@zenez.com>
ok Brian Gernhardt <benji@silverinsanity.com>
diff --git a/src/block-sha1/sha1.c b/src/block-sha1/sha1.c
new file mode 100644
index 000000000..50b20c4bd
--- /dev/null
+++ b/src/block-sha1/sha1.c
@@ -0,0 +1,280 @@
+/*
+ * 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 "common.h"
+#include "sha1.h"
+
+#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->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]);
+}
diff --git a/src/block-sha1/sha1.h b/src/block-sha1/sha1.h
new file mode 100644
index 000000000..b864df623
--- /dev/null
+++ b/src/block-sha1/sha1.h
@@ -0,0 +1,22 @@
+/*
+ * 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.
+ */
+
+typedef struct {
+ unsigned long long size;
+ unsigned int H[5];
+ unsigned int W[16];
+} blk_SHA_CTX;
+
+void blk_SHA1_Init(blk_SHA_CTX *ctx);
+void blk_SHA1_Update(blk_SHA_CTX *ctx, const void *dataIn, unsigned long len);
+void blk_SHA1_Final(unsigned char hashout[20], blk_SHA_CTX *ctx);
+
+#define git_SHA_CTX blk_SHA_CTX
+#define git_SHA1_Init blk_SHA1_Init
+#define git_SHA1_Update blk_SHA1_Update
+#define git_SHA1_Final blk_SHA1_Final
diff --git a/src/bswap.h b/src/bswap.h
new file mode 100644
index 000000000..0dac883d0
--- /dev/null
+++ b/src/bswap.h
@@ -0,0 +1,50 @@
+/*
+ * Let's make sure we always have a sane definition for ntohl()/htonl().
+ * Some libraries define those as a function call, just to perform byte
+ * shifting, bringing significant overhead to what should be a simple
+ * operation.
+ */
+
+#include "common.h"
+
+/*
+ * Default version that the compiler ought to optimize properly with
+ * constant values.
+ */
+static inline uint32_t default_swab32(uint32_t val)
+{
+ return (((val & 0xff000000) >> 24) |
+ ((val & 0x00ff0000) >> 8) |
+ ((val & 0x0000ff00) << 8) |
+ ((val & 0x000000ff) << 24));
+}
+
+#undef bswap32
+
+#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
+
+#define bswap32(x) ({ \
+ uint32_t __res; \
+ if (__builtin_constant_p(x)) { \
+ __res = default_swab32(x); \
+ } else { \
+ __asm__("bswap %0" : "=r" (__res) : "0" ((uint32_t)(x))); \
+ } \
+ __res; })
+
+#elif defined(_MSC_VER) && (defined(_M_IX86) || defined(_M_X64))
+
+#include <stdlib.h>
+
+#define bswap32(x) _byteswap_ulong(x)
+
+#endif
+
+#ifdef bswap32
+
+#undef ntohl
+#undef htonl
+#define ntohl(x) bswap32(x)
+#define htonl(x) bswap32(x)
+
+#endif
diff --git a/src/common.h b/src/common.h
index 18c321ca3..ff87c872c 100644
--- a/src/common.h
+++ b/src/common.h
@@ -50,6 +50,7 @@ typedef SSIZE_T ssize_t;
#include "util.h"
#include "thread-utils.h"
#include "errors.h"
+#include "bswap.h"
#define GIT_PATH_MAX 4096
diff --git a/src/hash.c b/src/hash.c
index 0051f0975..784b10b4b 100644
--- a/src/hash.c
+++ b/src/hash.c
@@ -25,10 +25,10 @@
#include "common.h"
#include "hash.h"
-#include SHA1_HEADER
+#include "sha1.h"
struct git_hash_ctx {
- SHA_CTX c;
+ git_SHA_CTX c;
};
git_hash_ctx *git_hash_new_ctx(void)
@@ -38,7 +38,7 @@ git_hash_ctx *git_hash_new_ctx(void)
if (!ctx)
return NULL;
- SHA1_Init(&ctx->c);
+ git_SHA1_Init(&ctx->c);
return ctx;
}
@@ -51,37 +51,37 @@ void git_hash_free_ctx(git_hash_ctx *ctx)
void git_hash_init(git_hash_ctx *ctx)
{
assert(ctx);
- SHA1_Init(&ctx->c);
+ git_SHA1_Init(&ctx->c);
}
void git_hash_update(git_hash_ctx *ctx, const void *data, size_t len)
{
assert(ctx);
- SHA1_Update(&ctx->c, data, len);
+ git_SHA1_Update(&ctx->c, data, len);
}
void git_hash_final(git_oid *out, git_hash_ctx *ctx)
{
assert(ctx);
- SHA1_Final(out->id, &ctx->c);
+ git_SHA1_Final(out->id, &ctx->c);
}
void git_hash_buf(git_oid *out, const void *data, size_t len)
{
- SHA_CTX c;
+ git_SHA_CTX c;
- SHA1_Init(&c);
- SHA1_Update(&c, data, len);
- SHA1_Final(out->id, &c);
+ git_SHA1_Init(&c);
+ git_SHA1_Update(&c, data, len);
+ git_SHA1_Final(out->id, &c);
}
void git_hash_vec(git_oid *out, git_buf_vec *vec, size_t n)
{
- SHA_CTX c;
+ git_SHA_CTX c;
size_t i;
- SHA1_Init(&c);
+ git_SHA1_Init(&c);
for (i = 0; i < n; i++)
- SHA1_Update(&c, vec[i].data, vec[i].len);
- SHA1_Final(out->id, &c);
+ git_SHA1_Update(&c, vec[i].data, vec[i].len);
+ git_SHA1_Final(out->id, &c);
}
diff --git a/src/ppc/sha1.c b/src/ppc/sha1.c
new file mode 100644
index 000000000..ec6a1926d
--- /dev/null
+++ b/src/ppc/sha1.c
@@ -0,0 +1,72 @@
+/*
+ * SHA-1 implementation.
+ *
+ * Copyright (C) 2005 Paul Mackerras <paulus@samba.org>
+ *
+ * This version assumes we are running on a big-endian machine.
+ * It calls an external sha1_core() to process blocks of 64 bytes.
+ */
+#include <stdio.h>
+#include <string.h>
+#include "sha1.h"
+
+extern void ppc_sha1_core(uint32_t *hash, const unsigned char *p,
+ unsigned int nblocks);
+
+int ppc_SHA1_Init(ppc_SHA_CTX *c)
+{
+ c->hash[0] = 0x67452301;
+ c->hash[1] = 0xEFCDAB89;
+ c->hash[2] = 0x98BADCFE;
+ c->hash[3] = 0x10325476;
+ c->hash[4] = 0xC3D2E1F0;
+ c->len = 0;
+ c->cnt = 0;
+ return 0;
+}
+
+int ppc_SHA1_Update(ppc_SHA_CTX *c, const void *ptr, unsigned long n)
+{
+ unsigned long nb;
+ const unsigned char *p = ptr;
+
+ c->len += (uint64_t) n << 3;
+ while (n != 0) {
+ if (c->cnt || n < 64) {
+ nb = 64 - c->cnt;
+ if (nb > n)
+ nb = n;
+ memcpy(&c->buf.b[c->cnt], p, nb);
+ if ((c->cnt += nb) == 64) {
+ ppc_sha1_core(c->hash, c->buf.b, 1);
+ c->cnt = 0;
+ }
+ } else {
+ nb = n >> 6;
+ ppc_sha1_core(c->hash, p, nb);
+ nb <<= 6;
+ }
+ n -= nb;
+ p += nb;
+ }
+ return 0;
+}
+
+int ppc_SHA1_Final(unsigned char *hash, ppc_SHA_CTX *c)
+{
+ unsigned int cnt = c->cnt;
+
+ c->buf.b[cnt++] = 0x80;
+ if (cnt > 56) {
+ if (cnt < 64)
+ memset(&c->buf.b[cnt], 0, 64 - cnt);
+ ppc_sha1_core(c->hash, c->buf.b, 1);
+ cnt = 0;
+ }
+ if (cnt < 56)
+ memset(&c->buf.b[cnt], 0, 56 - cnt);
+ c->buf.l[7] = c->len;
+ ppc_sha1_core(c->hash, c->buf.b, 1);
+ memcpy(hash, c->hash, 20);
+ return 0;
+}
diff --git a/src/ppc/sha1.h b/src/ppc/sha1.h
new file mode 100644
index 000000000..c405f734c
--- /dev/null
+++ b/src/ppc/sha1.h
@@ -0,0 +1,25 @@
+/*
+ * SHA-1 implementation.
+ *
+ * Copyright (C) 2005 Paul Mackerras <paulus@samba.org>
+ */
+#include <stdint.h>
+
+typedef struct {
+ uint32_t hash[5];
+ uint32_t cnt;
+ uint64_t len;
+ union {
+ unsigned char b[64];
+ uint64_t l[8];
+ } buf;
+} ppc_SHA_CTX;
+
+int ppc_SHA1_Init(ppc_SHA_CTX *c);
+int ppc_SHA1_Update(ppc_SHA_CTX *c, const void *p, unsigned long n);
+int ppc_SHA1_Final(unsigned char *hash, ppc_SHA_CTX *c);
+
+#define git_SHA_CTX ppc_SHA_CTX
+#define git_SHA1_Init ppc_SHA1_Init
+#define git_SHA1_Update ppc_SHA1_Update
+#define git_SHA1_Final ppc_SHA1_Final
diff --git a/src/ppc/sha1ppc.S b/src/ppc/sha1ppc.S
new file mode 100644
index 000000000..1711eef6e
--- /dev/null
+++ b/src/ppc/sha1ppc.S
@@ -0,0 +1,224 @@
+/*
+ * SHA-1 implementation for PowerPC.
+ *
+ * Copyright (C) 2005 Paul Mackerras <paulus@samba.org>
+ */
+
+/*
+ * PowerPC calling convention:
+ * %r0 - volatile temp
+ * %r1 - stack pointer.
+ * %r2 - reserved
+ * %r3-%r12 - Incoming arguments & return values; volatile.
+ * %r13-%r31 - Callee-save registers
+ * %lr - Return address, volatile
+ * %ctr - volatile
+ *
+ * Register usage in this routine:
+ * %r0 - temp
+ * %r3 - argument (pointer to 5 words of SHA state)
+ * %r4 - argument (pointer to data to hash)
+ * %r5 - Constant K in SHA round (initially number of blocks to hash)
+ * %r6-%r10 - Working copies of SHA variables A..E (actually E..A order)
+ * %r11-%r26 - Data being hashed W[].
+ * %r27-%r31 - Previous copies of A..E, for final add back.
+ * %ctr - loop count
+ */
+
+
+/*
+ * We roll the registers for A, B, C, D, E around on each
+ * iteration; E on iteration t is D on iteration t+1, and so on.
+ * We use registers 6 - 10 for this. (Registers 27 - 31 hold
+ * the previous values.)
+ */
+#define RA(t) (((t)+4)%5+6)
+#define RB(t) (((t)+3)%5+6)
+#define RC(t) (((t)+2)%5+6)
+#define RD(t) (((t)+1)%5+6)
+#define RE(t) (((t)+0)%5+6)
+
+/* We use registers 11 - 26 for the W values */
+#define W(t) ((t)%16+11)
+
+/* Register 5 is used for the constant k */
+
+/*
+ * The basic SHA-1 round function is:
+ * E += ROTL(A,5) + F(B,C,D) + W[i] + K; B = ROTL(B,30)
+ * Then the variables are renamed: (A,B,C,D,E) = (E,A,B,C,D).
+ *
+ * Every 20 rounds, the function F() and the constant K changes:
+ * - 20 rounds of f0(b,c,d) = "bit wise b ? c : d" = (^b & d) + (b & c)
+ * - 20 rounds of f1(b,c,d) = b^c^d = (b^d)^c
+ * - 20 rounds of f2(b,c,d) = majority(b,c,d) = (b&d) + ((b^d)&c)
+ * - 20 more rounds of f1(b,c,d)
+ *
+ * These are all scheduled for near-optimal performance on a G4.
+ * The G4 is a 3-issue out-of-order machine with 3 ALUs, but it can only
+ * *consider* starting the oldest 3 instructions per cycle. So to get
+ * maximum performance out of it, you have to treat it as an in-order
+ * machine. Which means interleaving the computation round t with the
+ * computation of W[t+4].
+ *
+ * The first 16 rounds use W values loaded directly from memory, while the
+ * remaining 64 use values computed from those first 16. We preload
+ * 4 values before starting, so there are three kinds of rounds:
+ * - The first 12 (all f0) also load the W values from memory.
+ * - The next 64 compute W(i+4) in parallel. 8*f0, 20*f1, 20*f2, 16*f1.
+ * - The last 4 (all f1) do not do anything with W.
+ *
+ * Therefore, we have 6 different round functions:
+ * STEPD0_LOAD(t,s) - Perform round t and load W(s). s < 16
+ * STEPD0_UPDATE(t,s) - Perform round t and compute W(s). s >= 16.
+ * STEPD1_UPDATE(t,s)
+ * STEPD2_UPDATE(t,s)
+ * STEPD1(t) - Perform round t with no load or update.
+ *
+ * The G5 is more fully out-of-order, and can find the parallelism
+ * by itself. The big limit is that it has a 2-cycle ALU latency, so
+ * even though it's 2-way, the code has to be scheduled as if it's
+ * 4-way, which can be a limit. To help it, we try to schedule the
+ * read of RA(t) as late as possible so it doesn't stall waiting for
+ * the previous round's RE(t-1), and we try to rotate RB(t) as early
+ * as possible while reading RC(t) (= RB(t-1)) as late as possible.
+ */
+
+/* the initial loads. */
+#define LOADW(s) \
+ lwz W(s),(s)*4(%r4)
+
+/*
+ * Perform a step with F0, and load W(s). Uses W(s) as a temporary
+ * before loading it.
+ * This is actually 10 instructions, which is an awkward fit.
+ * It can execute grouped as listed, or delayed one instruction.
+ * (If delayed two instructions, there is a stall before the start of the
+ * second line.) Thus, two iterations take 7 cycles, 3.5 cycles per round.
+ */
+#define STEPD0_LOAD(t,s) \
+add RE(t),RE(t),W(t); andc %r0,RD(t),RB(t); and W(s),RC(t),RB(t); \
+add RE(t),RE(t),%r0; rotlwi %r0,RA(t),5; rotlwi RB(t),RB(t),30; \
+add RE(t),RE(t),W(s); add %r0,%r0,%r5; lwz W(s),(s)*4(%r4); \
+add RE(t),RE(t),%r0
+
+/*
+ * This is likewise awkward, 13 instructions. However, it can also
+ * execute starting with 2 out of 3 possible moduli, so it does 2 rounds
+ * in 9 cycles, 4.5 cycles/round.
+ */
+#define STEPD0_UPDATE(t,s,loadk...) \
+add RE(t),RE(t),W(t); andc %r0,RD(t),RB(t); xor W(s),W((s)-16),W((s)-3); \
+add RE(t),RE(t),%r0; and %r0,RC(t),RB(t); xor W(s),W(s),W((s)-8); \
+add RE(t),RE(t),%r0; rotlwi %r0,RA(t),5; xor W(s),W(s),W((s)-14); \
+add RE(t),RE(t),%r5; loadk; rotlwi RB(t),RB(t),30; rotlwi W(s),W(s),1; \
+add RE(t),RE(t),%r0
+
+/* Nicely optimal. Conveniently, also the most common. */
+#define STEPD1_UPDATE(t,s,loadk...) \
+add RE(t),RE(t),W(t); xor %r0,RD(t),RB(t); xor W(s),W((s)-16),W((s)-3); \
+add RE(t),RE(t),%r5; loadk; xor %r0,%r0,RC(t); xor W(s),W(s),W((s)-8); \
+add RE(t),RE(t),%r0; rotlwi %r0,RA(t),5; xor W(s),W(s),W((s)-14); \
+add RE(t),RE(t),%r0; rotlwi RB(t),RB(t),30; rotlwi W(s),W(s),1
+
+/*
+ * The naked version, no UPDATE, for the last 4 rounds. 3 cycles per.
+ * We could use W(s) as a temp register, but we don't need it.
+ */
+#define STEPD1(t) \
+ add RE(t),RE(t),W(t); xor %r0,RD(t),RB(t); \
+rotlwi RB(t),RB(t),30; add RE(t),RE(t),%r5; xor %r0,%r0,RC(t); \
+add RE(t),RE(t),%r0; rotlwi %r0,RA(t),5; /* spare slot */ \
+add RE(t),RE(t),%r0
+
+/*
+ * 14 instructions, 5 cycles per. The majority function is a bit
+ * awkward to compute. This can execute with a 1-instruction delay,
+ * but it causes a 2-instruction delay, which triggers a stall.
+ */
+#define STEPD2_UPDATE(t,s,loadk...) \
+add RE(t),RE(t),W(t); and %r0,RD(t),RB(t); xor W(s),W((s)-16),W((s)-3); \
+add RE(t),RE(t),%r0; xor %r0,RD(t),RB(t); xor W(s),W(s),W((s)-8); \
+add RE(t),RE(t),%r5; loadk; and %r0,%r0,RC(t); xor W(s),W(s),W((s)-14); \
+add RE(t),RE(t),%r0; rotlwi %r0,RA(t),5; rotlwi W(s),W(s),1; \
+add RE(t),RE(t),%r0; rotlwi RB(t),RB(t),30
+
+#define STEP0_LOAD4(t,s) \
+ STEPD0_LOAD(t,s); \
+ STEPD0_LOAD((t+1),(s)+1); \
+ STEPD0_LOAD((t)+2,(s)+2); \
+ STEPD0_LOAD((t)+3,(s)+3)
+
+#define STEPUP4(fn, t, s, loadk...) \
+ STEP##fn##_UPDATE(t,s,); \
+ STEP##fn##_UPDATE((t)+1,(s)+1,); \
+ STEP##fn##_UPDATE((t)+2,(s)+2,); \
+ STEP##fn##_UPDATE((t)+3,(s)+3,loadk)
+
+#define STEPUP20(fn, t, s, loadk...) \
+ STEPUP4(fn, t, s,); \
+ STEPUP4(fn, (t)+4, (s)+4,); \
+ STEPUP4(fn, (t)+8, (s)+8,); \
+ STEPUP4(fn, (t)+12, (s)+12,); \
+ STEPUP4(fn, (t)+16, (s)+16, loadk)
+
+ .globl ppc_sha1_core
+ppc_sha1_core:
+ stwu %r1,-80(%r1)
+ stmw %r13,4(%r1)
+
+ /* Load up A - E */
+ lmw %r27,0(%r3)
+
+ mtctr %r5
+
+1:
+ LOADW(0)
+ lis %r5,0x5a82
+ mr RE(0),%r31
+ LOADW(1)
+ mr RD(0),%r30
+ mr RC(0),%r29
+ LOADW(2)
+ ori %r5,%r5,0x7999 /* K0-19 */
+ mr RB(0),%r28
+ LOADW(3)
+ mr RA(0),%r27
+
+ STEP0_LOAD4(0, 4)
+ STEP0_LOAD4(4, 8)
+ STEP0_LOAD4(8, 12)
+ STEPUP4(D0, 12, 16,)
+ STEPUP4(D0, 16, 20, lis %r5,0x6ed9)
+
+ ori %r5,%r5,0xeba1 /* K20-39 */
+ STEPUP20(D1, 20, 24, lis %r5,0x8f1b)
+
+ ori %r5,%r5,0xbcdc /* K40-59 */
+ STEPUP20(D2, 40, 44, lis %r5,0xca62)
+
+ ori %r5,%r5,0xc1d6 /* K60-79 */
+ STEPUP4(D1, 60, 64,)
+ STEPUP4(D1, 64, 68,)
+ STEPUP4(D1, 68, 72,)
+ STEPUP4(D1, 72, 76,)
+ addi %r4,%r4,64
+ STEPD1(76)
+ STEPD1(77)
+ STEPD1(78)
+ STEPD1(79)
+
+ /* Add results to original values */
+ add %r31,%r31,RE(0)
+ add %r30,%r30,RD(0)
+ add %r29,%r29,RC(0)
+ add %r28,%r28,RB(0)
+ add %r27,%r27,RA(0)
+
+ bdnz 1b
+
+ /* Save final hash, restore registers, and return */
+ stmw %r27,0(%r3)
+ lmw %r13,4(%r1)
+ addi %r1,%r1,80
+ blr
diff --git a/src/sha1.h b/src/sha1.h
new file mode 100644
index 000000000..ac3e84651
--- /dev/null
+++ b/src/sha1.h
@@ -0,0 +1,10 @@
+#ifndef INCLUDE_sha1_h__
+#define INCLUDE_sha1_h__
+
+#ifdef PPC_SHA1
+# include "ppc/sha1.h"
+#else
+# include "block-sha1/sha1.h"
+#endif
+
+#endif /* INCLUDE_sha1_h__ */
diff --git a/src/sha1/sha1.c b/src/sha1/sha1.c
deleted file mode 100644
index 833ae912e..000000000
--- a/src/sha1/sha1.c
+++ /dev/null
@@ -1,170 +0,0 @@
-/*
- * The contents of this file are subject to the Mozilla Public
- * License Version 1.1 (the "License"); you may not use this file
- * except in compliance with the License. You may obtain a copy of
- * the License at http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS
- * IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
- * implied. See the License for the specific language governing
- * rights and limitations under the License.
- *
- * The Original Code is SHA 180-1 Reference Implementation (Compact version)
- *
- * The Initial Developer of the Original Code is Paul Kocher of
- * Cryptography Research. Portions created by Paul Kocher are
- * Copyright (C) 1995-9 by Cryptography Research, Inc. All
- * Rights Reserved.
- *
- * Contributor(s):
- *
- * Paul Kocher
- *
- * Alternatively, the contents of this file may be used under the
- * terms of the GNU General Public License, version 2, (the "GPL")
- * as published by the Free Software Foundation.
- *
- * In addition to the permissions in the GNU General Public License,
- * the authors give you unlimited permission to link the compiled
- * version of this file into combinations with other programs,
- * and to distribute those combinations without any restriction
- * coming from the use of this file. (The General Public License
- * restrictions do apply in other respects; for example, they cover
- * modification of the file, and distribution when not linked into
- * a combined executable.)
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; see the file COPYING. If not, write to
- * the Free Software Foundation, 51 Franklin Street, Fifth Floor,
- * Boston, MA 02110-1301, USA.
- *
- * If you wish to allow use of your version of this file only under
- * the terms of the GPL and not to allow others to use your version
- * of this file under the MPL, indicate your decision by deleting
- * the provisions above and replace them with the notice and other
- * provisions required by the GPL. If you do not delete the
- * provisions above, a recipient may use your version of this file
- * under either the MPL or the GPL.
- */
-
-#include "sha1.h"
-
-static void shaHashBlock(SHA_CTX *ctx);
-
-void SHA1_Init(SHA_CTX *ctx) {
- int i;
-
- ctx->lenW = 0;
- ctx->sizeHi = ctx->sizeLo = 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;
-
- for (i = 0; i < 80; i++)
- ctx->W[i] = 0;
-}
-
-
-void SHA1_Update(SHA_CTX *ctx, const void *_dataIn, int len) {
- const unsigned char *dataIn = _dataIn;
- int i;
-
- /* Read the data into W and process blocks as they get full
- */
- for (i = 0; i < len; i++) {
- ctx->W[ctx->lenW / 4] <<= 8;
- ctx->W[ctx->lenW / 4] |= (unsigned int)dataIn[i];
- if ((++ctx->lenW) % 64 == 0) {
- shaHashBlock(ctx);
- ctx->lenW = 0;
- }
- ctx->sizeLo += 8;
- ctx->sizeHi += (ctx->sizeLo < 8);
- }
-}
-
-
-void SHA1_Final(unsigned char hashout[20], SHA_CTX *ctx) {
- unsigned char pad0x80 = 0x80;
- unsigned char pad0x00 = 0x00;
- unsigned char padlen[8];
- int i;
-
- /* Pad with a binary 1 (e.g. 0x80), then zeroes, then length
- */
- padlen[0] = (unsigned char)((ctx->sizeHi >> 24) & 255);
- padlen[1] = (unsigned char)((ctx->sizeHi >> 16) & 255);
- padlen[2] = (unsigned char)((ctx->sizeHi >> 8) & 255);
- padlen[3] = (unsigned char)((ctx->sizeHi >> 0) & 255);
- padlen[4] = (unsigned char)((ctx->sizeLo >> 24) & 255);
- padlen[5] = (unsigned char)((ctx->sizeLo >> 16) & 255);
- padlen[6] = (unsigned char)((ctx->sizeLo >> 8) & 255);
- padlen[7] = (unsigned char)((ctx->sizeLo >> 0) & 255);
- SHA1_Update(ctx, &pad0x80, 1);
- while (ctx->lenW != 56)
- SHA1_Update(ctx, &pad0x00, 1);
- SHA1_Update(ctx, padlen, 8);
-
- /* Output hash
- */
- for (i = 0; i < 20; i++) {
- hashout[i] = (unsigned char)(ctx->H[i / 4] >> 24);
- ctx->H[i / 4] <<= 8;
- }
-
- /*
- * Re-initialize the context (also zeroizes contents)
- */
- SHA1_Init(ctx);
-}
-
-
-#define SHA_ROT(X,n) (((X) << (n)) | ((X) >> (32-(n))))
-
-static void shaHashBlock(SHA_CTX *ctx) {
- int t;
- unsigned int A,B,C,D,E,TEMP;
-
- for (t = 16; t <= 79; t++)
- ctx->W[t] =
- SHA_ROT(ctx->W[t-3] ^ ctx->W[t-8] ^ ctx->W[t-14] ^ ctx->W[t-16], 1);
-
- A = ctx->H[0];
- B = ctx->H[1];
- C = ctx->H[2];
- D = ctx->H[3];
- E = ctx->H[4];
-
- for (t = 0; t <= 19; t++) {
- TEMP = SHA_ROT(A,5) + (((C^D)&B)^D) + E + ctx->W[t] + 0x5a827999;
- E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
- }
- for (t = 20; t <= 39; t++) {
- TEMP = SHA_ROT(A,5) + (B^C^D) + E + ctx->W[t] + 0x6ed9eba1;
- E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
- }
- for (t = 40; t <= 59; t++) {
- TEMP = SHA_ROT(A,5) + ((B&C)|(D&(B|C))) + E + ctx->W[t] + 0x8f1bbcdc;
- E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
- }
- for (t = 60; t <= 79; t++) {
- TEMP = SHA_ROT(A,5) + (B^C^D) + E + ctx->W[t] + 0xca62c1d6;
- E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
- }
-
- ctx->H[0] += A;
- ctx->H[1] += B;
- ctx->H[2] += C;
- ctx->H[3] += D;
- ctx->H[4] += E;
-}
diff --git a/src/sha1/sha1.h b/src/sha1/sha1.h
deleted file mode 100644
index cb5245e80..000000000
--- a/src/sha1/sha1.h
+++ /dev/null
@@ -1,64 +0,0 @@
-/*
- * The contents of this file are subject to the Mozilla Public
- * License Version 1.1 (the "License"); you may not use this file
- * except in compliance with the License. You may obtain a copy of
- * the License at http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS
- * IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
- * implied. See the License for the specific language governing
- * rights and limitations under the License.
- *
- * The Original Code is SHA 180-1 Header File
- *
- * The Initial Developer of the Original Code is Paul Kocher of
- * Cryptography Research. Portions created by Paul Kocher are
- * Copyright (C) 1995-9 by Cryptography Research, Inc. All
- * Rights Reserved.
- *
- * Contributor(s):
- *
- * Paul Kocher
- *
- * Alternatively, the contents of this file may be used under the
- * terms of the GNU General Public License, version 2, (the "GPL")
- * as published by the Free Software Foundation.
- *
- * In addition to the permissions in the GNU General Public License,
- * the authors give you unlimited permission to link the compiled
- * version of this file into combinations with other programs,
- * and to distribute those combinations without any restriction
- * coming from the use of this file. (The General Public License
- * restrictions do apply in other respects; for example, they cover
- * modification of the file, and distribution when not linked into
- * a combined executable.)
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; see the file COPYING. If not, write to
- * the Free Software Foundation, 51 Franklin Street, Fifth Floor,
- * Boston, MA 02110-1301, USA.
- *
- * If you wish to allow use of your version of this file only under
- * the terms of the GPL and not to allow others to use your version
- * of this file under the MPL, indicate your decision by deleting
- * the provisions above and replace them with the notice and other
- * provisions required by the GPL. If you do not delete the
- * provisions above, a recipient may use your version of this file
- * under either the MPL or the GPL.
- */
-
-typedef struct {
- unsigned int H[5];
- unsigned int W[80];
- int lenW;
- unsigned int sizeHi,sizeLo;
-} SHA_CTX;
-
-void SHA1_Init(SHA_CTX *ctx);
-void SHA1_Update(SHA_CTX *ctx, const void *dataIn, int len);
-void SHA1_Final(unsigned char hashout[20], SHA_CTX *ctx);
View Lorry Controller Status