Commit 7205a4d94cdead95c397505292a31b4854039825

Carlos Martín Nieto 2012-10-23T19:30:04

Use libcrypto's SHA-1 implementation when linking to it libcryto's SHA-1 implementation is measurably better than the one that ships with the library. If we link to it for HTTPS support already, use that implementation instead. Testing on a ~600MB of the linux repository, this reduces indexing time by 40% and removes the hashing from the top spot in the perf output.

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 5292906..434fba9 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -40,8 +40,10 @@ ENDIF()
 IF (SHA1_TYPE STREQUAL "ppc")
 	ADD_DEFINITIONS(-DPPC_SHA1)
 	FILE(GLOB SRC_SHA1 src/ppc/*.c src/ppc/*.S)
+ELSEIF (OPENSSL_FOUND) # libcrypto's implementation is faster than ours
+	ADD_DEFINITIONS(-DOPENSSL_SHA)
 ELSE ()
-	SET (SRC_SHA1)
+	FILE(GLOB SRC_SHA1 src/sha1/*.c)
 ENDIF()
 
 IF (NOT WIN32)
@@ -198,7 +200,7 @@ IF (BUILD_CLAR)
 		DEPENDS ${CLAR_PATH}/clar ${SRC_TEST}
 		WORKING_DIRECTORY ${CLAR_PATH}
 	)
-	ADD_EXECUTABLE(libgit2_clar ${SRC} ${CLAR_PATH}/clar_main.c ${SRC_TEST} ${SRC_ZLIB} ${SRC_HTTP} ${SRC_REGEX})
+	ADD_EXECUTABLE(libgit2_clar ${SRC} ${CLAR_PATH}/clar_main.c ${SRC_TEST} ${SRC_ZLIB} ${SRC_HTTP} ${SRC_REGEX} ${SRC_SHA1})
 	TARGET_LINK_LIBRARIES(libgit2_clar ${CMAKE_THREAD_LIBS_INIT} ${SSL_LIBRARIES})
 
         IF (MSVC)
diff --git a/src/sha1.c b/src/sha1.c
deleted file mode 100644
index 8aaedeb..0000000
--- a/src/sha1.c
+++ /dev/null
@@ -1,280 +0,0 @@
-/*
- * Copyright (C) 2009-2012 the libgit2 contributors
- *
- * This file is part of libgit2, distributed under the GNU GPL v2 with
- * a Linking Exception. For full terms see the included COPYING file.
- */
-
-#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(_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);
-	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 git__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 git__blk_SHA1_Update(blk_SHA_CTX *ctx, const void *data, size_t len)
-{
-	unsigned int lenW = ctx->size & 63;
-
-	ctx->size += len;
-
-	/* Read the data into W and process blocks as they get full */
-	if (lenW) {
-		unsigned int left = 64 - lenW;
-		if (len < left)
-			left = (unsigned int)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 git__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((uint32_t)(ctx->size >> 29));
-	padlen[1] = htonl((uint32_t)(ctx->size << 3));
-
-	i = ctx->size & 63;
-	git__blk_SHA1_Update(ctx, pad, 1+ (63 & (55 - i)));
-	git__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/sha1.h b/src/sha1.h
index f0a16f2..41e8aba 100644
--- a/src/sha1.h
+++ b/src/sha1.h
@@ -8,12 +8,17 @@
 #ifndef INCLUDE_sha1_h__
 #define INCLUDE_sha1_h__
 
+#ifdef OPENSSL_SHA
+# include <openssl/sha.h>
+
+#else
 typedef struct {
 	unsigned long long size;
 	unsigned int H[5];
 	unsigned int W[16];
 } blk_SHA_CTX;
 
+
 void git__blk_SHA1_Init(blk_SHA_CTX *ctx);
 void git__blk_SHA1_Update(blk_SHA_CTX *ctx, const void *dataIn, size_t len);
 void git__blk_SHA1_Final(unsigned char hashout[20], blk_SHA_CTX *ctx);
@@ -23,4 +28,6 @@ void git__blk_SHA1_Final(unsigned char hashout[20], blk_SHA_CTX *ctx);
 #define SHA1_Update	git__blk_SHA1_Update
 #define SHA1_Final	git__blk_SHA1_Final
 
+#endif // OPENSSL_SHA
+
 #endif
diff --git a/src/sha1/sha1.c b/src/sha1/sha1.c
new file mode 100644
index 0000000..8aaedeb
--- /dev/null
+++ b/src/sha1/sha1.c
@@ -0,0 +1,280 @@
+/*
+ * Copyright (C) 2009-2012 the libgit2 contributors
+ *
+ * This file is part of libgit2, distributed under the GNU GPL v2 with
+ * a Linking Exception. For full terms see the included COPYING file.
+ */
+
+#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(_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);
+	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 git__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 git__blk_SHA1_Update(blk_SHA_CTX *ctx, const void *data, size_t len)
+{
+	unsigned int lenW = ctx->size & 63;
+
+	ctx->size += len;
+
+	/* Read the data into W and process blocks as they get full */
+	if (lenW) {
+		unsigned int left = 64 - lenW;
+		if (len < left)
+			left = (unsigned int)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 git__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((uint32_t)(ctx->size >> 29));
+	padlen[1] = htonl((uint32_t)(ctx->size << 3));
+
+	i = ctx->size & 63;
+	git__blk_SHA1_Update(ctx, pad, 1+ (63 & (55 - i)));
+	git__blk_SHA1_Update(ctx, padlen, 8);
+
+	/* Output hash */
+	for (i = 0; i < 5; i++)
+		put_be32(hashout + i*4, ctx->H[i]);
+}