Commit 5dddf7c855f9c8e43954a99a6f85c098dfc7ed41

Andreas Ericsson 2010-04-14T20:41:57

Add block-sha1 in favour of the mozilla routines Since block-sha1 from git.git has such excellent performance, we can also get rid of the openssl dependency. It's rather simple to add it back later as an optional extra, but we really needn't bother to pull in the entire ssl library and have to deal with linking issues now that we have the portable and, performance-wise, truly excellent block-sha1 code to fall back on. Since this requires a slight revamp of the build rules anyway, we take the opportunity to fix including EXTRA_OBJS in the final build as well. The block-sha1 code was originally implemented for git.git by Linus Torvalds <torvalds@linux-foundation.org> and was later polished by Nicolas Pitre <nico@cam.org>. Signed-off-by: Andreas Ericsson <ae@op5.se>

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
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
diff --git a/Makefile b/Makefile
index 73630ef..ff5f933 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
@@ -58,7 +55,7 @@ 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)
@@ -71,22 +68,21 @@ 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)
 
diff --git a/src/block-sha1/sha1.c b/src/block-sha1/sha1.c
new file mode 100644
index 0000000..50b20c4
--- /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 0000000..b864df6
--- /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 0000000..0dac883
--- /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 29a61a7..ae3a161 100644
--- a/src/common.h
+++ b/src/common.h
@@ -80,6 +80,7 @@ typedef __int64 off64_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 0051f09..784b10b 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/sha1.h b/src/sha1.h
new file mode 100644
index 0000000..ac3e846
--- /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 833ae91..0000000
--- 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 cb5245e..0000000
--- 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);