From: Linus Torvalds <torvalds@linux-foundation.org>
To: Git Mailing List <git@vger.kernel.org>,
Junio C Hamano <gitster@pobox.com>
Subject: [PATCH 1/7] block-sha1: add new optimized C 'block-sha1' routines
Date: Thu, 6 Aug 2009 08:15:39 -0700 (PDT) [thread overview]
Message-ID: <alpine.LFD.2.01.0908060814050.3390@localhost.localdomain> (raw)
In-Reply-To: <alpine.LFD.2.01.0908060803140.3390@localhost.localdomain>
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 5 Aug 2009 14:49:32 -0700
Subject: [PATCH 1/7] block-sha1: add new optimized C 'block-sha1' routines
Based ont he mozilla SHA1 routine, but doing the input data accesses a
word at a time and with 'htonl()' instead of loading bytes and shifting.
It requires an architecture that is ok with unaligned 32-bit loads and a
fast htonl().
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
Side note: we can get rid of the "arch must support unaligned loads"
requirement later on by telling the compiler which ones _can_ be
unaligned. So the limitations aren't all that fundamental, really.
Makefile | 9 +++
block-sha1/sha1.c | 145 +++++++++++++++++++++++++++++++++++++++++++++++++++++
block-sha1/sha1.h | 21 ++++++++
3 files changed, 175 insertions(+), 0 deletions(-)
diff --git a/Makefile b/Makefile
index d7669b1..f12024c 100644
--- a/Makefile
+++ b/Makefile
@@ -84,6 +84,10 @@ all::
# specify your own (or DarwinPort's) include directories and
# library directories by defining CFLAGS and LDFLAGS appropriately.
#
+# Define BLK_SHA1 environment variable if you want the C version
+# of the SHA1 that assumes you can do unaligned 32-bit loads and
+# have a fast htonl() function.
+#
# Define PPC_SHA1 environment variable when running make to make use of
# a bundled SHA1 routine optimized for PowerPC.
#
@@ -1166,6 +1170,10 @@ ifdef NO_DEFLATE_BOUND
BASIC_CFLAGS += -DNO_DEFLATE_BOUND
endif
+ifdef BLK_SHA1
+ SHA1_HEADER = "block-sha1/sha1.h"
+ LIB_OBJS += block-sha1/sha1.o
+else
ifdef PPC_SHA1
SHA1_HEADER = "ppc/sha1.h"
LIB_OBJS += ppc/sha1.o ppc/sha1ppc.o
@@ -1183,6 +1191,7 @@ else
endif
endif
endif
+endif
ifdef NO_PERL_MAKEMAKER
export NO_PERL_MAKEMAKER
endif
diff --git a/block-sha1/sha1.c b/block-sha1/sha1.c
new file mode 100644
index 0000000..eef32f7
--- /dev/null
+++ b/block-sha1/sha1.c
@@ -0,0 +1,145 @@
+/*
+ * Based on the Mozilla SHA1 (see mozilla-sha1/sha1.c),
+ * optimized to do word accesses rather than byte accesses,
+ * and to avoid unnecessary copies into the context array.
+ */
+
+#include <string.h>
+#include <arpa/inet.h>
+
+#include "sha1.h"
+
+/* Hash one 64-byte block of data */
+static void blk_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data);
+
+void blk_SHA1_Init(blk_SHA_CTX *ctx)
+{
+ ctx->lenW = 0;
+ 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->lenW;
+
+ ctx->size += (unsigned long long) len << 3;
+
+ /* 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;
+ ctx->lenW = lenW;
+ 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);
+ ctx->lenW = 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 >> 32);
+ padlen[1] = htonl(ctx->size);
+
+ blk_SHA1_Update(ctx, pad, 1+ (63 & (55 - ctx->lenW)));
+ blk_SHA1_Update(ctx, padlen, 8);
+
+ /* Output hash
+ */
+ for (i = 0; i < 5; i++)
+ ((unsigned int *)hashout)[i] = htonl(ctx->H[i]);
+}
+
+#define SHA_ROT(X,n) (((X) << (n)) | ((X) >> (32-(n))))
+
+static void blk_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data)
+{
+ int t;
+ unsigned int A,B,C,D,E,TEMP;
+ unsigned int W[80];
+
+ for (t = 0; t < 16; t++)
+ W[t] = htonl(data[t]);
+
+ /* Unroll it? */
+ for (t = 16; t <= 79; t++)
+ W[t] = SHA_ROT(W[t-3] ^ W[t-8] ^ W[t-14] ^ W[t-16], 1);
+
+ A = ctx->H[0];
+ B = ctx->H[1];
+ C = ctx->H[2];
+ D = ctx->H[3];
+ E = ctx->H[4];
+
+#define T_0_19(t) \
+ TEMP = SHA_ROT(A,5) + (((C^D)&B)^D) + E + W[t] + 0x5a827999; \
+ E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
+
+ T_0_19( 0); T_0_19( 1); T_0_19( 2); T_0_19( 3); T_0_19( 4);
+ T_0_19( 5); T_0_19( 6); T_0_19( 7); T_0_19( 8); T_0_19( 9);
+ T_0_19(10); T_0_19(11); T_0_19(12); T_0_19(13); T_0_19(14);
+ T_0_19(15); T_0_19(16); T_0_19(17); T_0_19(18); T_0_19(19);
+
+#define T_20_39(t) \
+ TEMP = SHA_ROT(A,5) + (B^C^D) + E + W[t] + 0x6ed9eba1; \
+ E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
+
+ T_20_39(20); T_20_39(21); T_20_39(22); T_20_39(23); T_20_39(24);
+ T_20_39(25); T_20_39(26); T_20_39(27); T_20_39(28); T_20_39(29);
+ T_20_39(30); T_20_39(31); T_20_39(32); T_20_39(33); T_20_39(34);
+ T_20_39(35); T_20_39(36); T_20_39(37); T_20_39(38); T_20_39(39);
+
+#define T_40_59(t) \
+ TEMP = SHA_ROT(A,5) + ((B&C)|(D&(B|C))) + E + W[t] + 0x8f1bbcdc; \
+ E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
+
+ T_40_59(40); T_40_59(41); T_40_59(42); T_40_59(43); T_40_59(44);
+ T_40_59(45); T_40_59(46); T_40_59(47); T_40_59(48); T_40_59(49);
+ T_40_59(50); T_40_59(51); T_40_59(52); T_40_59(53); T_40_59(54);
+ T_40_59(55); T_40_59(56); T_40_59(57); T_40_59(58); T_40_59(59);
+
+#define T_60_79(t) \
+ TEMP = SHA_ROT(A,5) + (B^C^D) + E + W[t] + 0xca62c1d6; \
+ E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
+
+ T_60_79(60); T_60_79(61); T_60_79(62); T_60_79(63); T_60_79(64);
+ T_60_79(65); T_60_79(66); T_60_79(67); T_60_79(68); T_60_79(69);
+ T_60_79(70); T_60_79(71); T_60_79(72); T_60_79(73); T_60_79(74);
+ T_60_79(75); T_60_79(76); T_60_79(77); T_60_79(78); T_60_79(79);
+
+ ctx->H[0] += A;
+ ctx->H[1] += B;
+ ctx->H[2] += C;
+ ctx->H[3] += D;
+ ctx->H[4] += E;
+}
diff --git a/block-sha1/sha1.h b/block-sha1/sha1.h
new file mode 100644
index 0000000..7be2d93
--- /dev/null
+++ b/block-sha1/sha1.h
@@ -0,0 +1,21 @@
+/*
+ * Based on the Mozilla SHA1 (see mozilla-sha1/sha1.h),
+ * optimized to do word accesses rather than byte accesses,
+ * and to avoid unnecessary copies into the context array.
+ */
+
+typedef struct {
+ unsigned int H[5];
+ unsigned int W[16];
+ int lenW;
+ unsigned long long size;
+} 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
--
1.6.4.31.g154b2.dirty
next prev parent reply other threads:[~2009-08-06 15:15 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-08-06 15:13 [PATCH 0/7] block-sha1: improved SHA1 hashing Linus Torvalds
2009-08-06 15:15 ` Linus Torvalds [this message]
2009-08-06 15:16 ` [PATCH 2/7] block-sha1: try to use rol/ror appropriately Linus Torvalds
2009-08-06 15:18 ` [PATCH 3/7] block-sha1: make the 'ntohl()' part of the first SHA1 loop Linus Torvalds
2009-08-06 15:20 ` [PATCH 4/7] block-sha1: re-use the temporary array as we calculate the SHA1 Linus Torvalds
2009-08-06 15:22 ` [PATCH 5/7] block-sha1: macroize the rounds a bit further Linus Torvalds
2009-08-06 15:24 ` [PATCH 6/7] block-sha1: Use '(B&C)+(D&(B^C))' instead of '(B&C)|(D&(B|C))' in round 3 Linus Torvalds
2009-08-06 15:25 ` [PATCH 7/7] block-sha1: get rid of redundant 'lenW' context Linus Torvalds
2009-08-06 18:25 ` [PATCH 2/7] block-sha1: try to use rol/ror appropriately Bert Wesarg
2009-08-06 17:22 ` [PATCH 0/7] block-sha1: improved SHA1 hashing Artur Skawina
2009-08-06 18:09 ` Linus Torvalds
2009-08-06 19:10 ` Artur Skawina
2009-08-06 19:41 ` Linus Torvalds
2009-08-06 20:08 ` Artur Skawina
2009-08-06 20:53 ` Linus Torvalds
2009-08-06 21:24 ` Linus Torvalds
2009-08-06 21:39 ` Artur Skawina
2009-08-06 21:52 ` Artur Skawina
2009-08-06 22:27 ` Linus Torvalds
2009-08-06 22:33 ` Linus Torvalds
2009-08-06 23:19 ` Artur Skawina
2009-08-06 23:42 ` Linus Torvalds
2009-08-06 22:55 ` Artur Skawina
2009-08-06 23:04 ` Linus Torvalds
2009-08-06 23:25 ` Linus Torvalds
2009-08-07 0:13 ` Linus Torvalds
2009-08-07 1:30 ` Artur Skawina
2009-08-07 1:55 ` Linus Torvalds
2009-08-07 0:53 ` Artur Skawina
2009-08-07 2:23 ` Linus Torvalds
2009-08-07 4:16 ` Artur Skawina
[not found] ` <alpine.LFD.2.01.0908071614310.3288@localhost.localdomain>
[not found] ` <4A7CBD28.6070306@gmail.com>
[not found] ` <4A7CBF47.9000903@gmail.com>
[not found] ` <alpine.LFD.2.01.0908071700290.3288@localhost.localdomain>
[not found] ` <4A7CC380.3070008@gmail.com>
2009-08-08 4:16 ` Linus Torvalds
2009-08-08 5:34 ` Artur Skawina
2009-08-08 17:10 ` Linus Torvalds
2009-08-08 18:12 ` Artur Skawina
2009-08-08 22:58 ` Artur Skawina
2009-08-08 23:36 ` Artur Skawina
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=alpine.LFD.2.01.0908060814050.3390@localhost.localdomain \
--to=torvalds@linux-foundation.org \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).