From 1ccf07cbb762b44746c49634e1c6fb945c9977df Mon Sep 17 00:00:00 2001
From: "brian m. carlson" <sandals@crustytoothpaste.net>
Date: Mon, 22 Oct 2018 02:43:31 +0000
Subject: [PATCH 01/12] sha1-file: rename algorithm to "sha1"
The transition plan anticipates us using a syntax such as "^{sha1}" for
disambiguation. Since this is a syntax some people will be typing a
lot, it makes sense to provide a short, easy-to-type syntax. Omitting
the dash doesn't create any ambiguity; however, it does make the syntax
shorter and easier to type, especially for touch typists. In addition,
the transition plan already uses "sha1" in this context.
Rename the name of SHA-1 implementation to "sha1".
Note that this change creates no backwards compatibility concerns, since
we haven't yet used this field in any configuration settings.
Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
sha1-file.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/sha1-file.c b/sha1-file.c
index a4367b8f04..e29825f259 100644
--- a/sha1-file.c
+++ b/sha1-file.c
@@ -97,7 +97,7 @@ const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = {
NULL,
},
{
- "sha-1",
+ "sha1",
/* "sha1", big-endian */
0x73686131,
GIT_SHA1_RAWSZ,
From 2f90b9d9b4ba1f8e79318853301e8ef19ca02681 Mon Sep 17 00:00:00 2001
From: "brian m. carlson" <sandals@crustytoothpaste.net>
Date: Mon, 22 Oct 2018 02:43:32 +0000
Subject: [PATCH 02/12] sha1-file: provide functions to look up hash algorithms
There are several ways we might refer to a hash algorithm: by name, such
as in the config file; by format ID, such as in a pack; or internally,
by a pointer to the hash_algos array. Provide functions to look up hash
algorithms based on these various forms and return the internal constant
used for them. If conversion to another form is necessary, this
internal constant can be used to look up the proper data in the
hash_algos array.
Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
hash.h | 13 +++++++++++++
sha1-file.c | 21 +++++++++++++++++++++
2 files changed, 34 insertions(+)
diff --git a/hash.h b/hash.h
index 7c8238bc2e..80881eea47 100644
--- a/hash.h
+++ b/hash.h
@@ -98,4 +98,17 @@ struct git_hash_algo {
};
extern const struct git_hash_algo hash_algos[GIT_HASH_NALGOS];
+/*
+ * Return a GIT_HASH_* constant based on the name. Returns GIT_HASH_UNKNOWN if
+ * the name doesn't match a known algorithm.
+ */
+int hash_algo_by_name(const char *name);
+/* Identical, except based on the format ID. */
+int hash_algo_by_id(uint32_t format_id);
+/* Identical, except for a pointer to struct git_hash_algo. */
+static inline int hash_algo_by_ptr(const struct git_hash_algo *p)
+{
+ return p - hash_algos;
+}
+
#endif
diff --git a/sha1-file.c b/sha1-file.c
index e29825f259..3a75d515eb 100644
--- a/sha1-file.c
+++ b/sha1-file.c
@@ -122,6 +122,27 @@ const char *empty_blob_oid_hex(void)
return oid_to_hex_r(buf, the_hash_algo->empty_blob);
}
+int hash_algo_by_name(const char *name)
+{
+ int i;
+ if (!name)
+ return GIT_HASH_UNKNOWN;
+ for (i = 1; i < GIT_HASH_NALGOS; i++)
+ if (!strcmp(name, hash_algos[i].name))
+ return i;
+ return GIT_HASH_UNKNOWN;
+}
+
+int hash_algo_by_id(uint32_t format_id)
+{
+ int i;
+ for (i = 1; i < GIT_HASH_NALGOS; i++)
+ if (format_id == hash_algos[i].format_id)
+ return i;
+ return GIT_HASH_UNKNOWN;
+}
+
+
/*
* This is meant to hold a *small* number of objects that you would
* want read_sha1_file() to be able to return, but yet you do not want
From 47edb649973cf5cd5f7066b5c936b330f78d687b Mon Sep 17 00:00:00 2001
From: "brian m. carlson" <sandals@crustytoothpaste.net>
Date: Wed, 14 Nov 2018 04:09:29 +0000
Subject: [PATCH 03/12] hex: introduce functions to print arbitrary hashes
Currently, we have functions that turn an arbitrary SHA-1 value or an
object ID into hex format, either using a static buffer or with a
user-provided buffer. Add variants of these functions that can handle
an arbitrary hash algorithm, specified by constant. Update the
documentation as well.
While we're at it, remove the "extern" declaration from this family of
functions, since it's not needed and our style now recommends against
it.
We use the variant taking the algorithm structure pointer as the
internal variant, since taking an algorithm pointer is the easiest way
to handle all of the variants in use.
Note that we maintain these functions because there are hashes which
must change based on the hash algorithm in use but are not object IDs
(such as pack checksums).
Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
cache.h | 15 +++++++++------
hex.c | 32 ++++++++++++++++++++++++--------
2 files changed, 33 insertions(+), 14 deletions(-)
diff --git a/cache.h b/cache.h
index d508f3d4f8..2ead61f05a 100644
--- a/cache.h
+++ b/cache.h
@@ -1361,9 +1361,9 @@ extern int get_oid_hex(const char *hex, struct object_id *sha1);
extern int hex_to_bytes(unsigned char *binary, const char *hex, size_t len);
/*
- * Convert a binary sha1 to its hex equivalent. The `_r` variant is reentrant,
+ * Convert a binary hash to its hex equivalent. The `_r` variant is reentrant,
* and writes the NUL-terminated output to the buffer `out`, which must be at
- * least `GIT_SHA1_HEXSZ + 1` bytes, and returns a pointer to out for
+ * least `GIT_MAX_HEXSZ + 1` bytes, and returns a pointer to out for
* convenience.
*
* The non-`_r` variant returns a static buffer, but uses a ring of 4
@@ -1371,10 +1371,13 @@ extern int hex_to_bytes(unsigned char *binary, const char *hex, size_t len);
*
* printf("%s -> %s", sha1_to_hex(one), sha1_to_hex(two));
*/
-extern char *sha1_to_hex_r(char *out, const unsigned char *sha1);
-extern char *oid_to_hex_r(char *out, const struct object_id *oid);
-extern char *sha1_to_hex(const unsigned char *sha1); /* static buffer result! */
-extern char *oid_to_hex(const struct object_id *oid); /* same static buffer as sha1_to_hex */
+char *hash_to_hex_algop_r(char *buffer, const unsigned char *hash, const struct git_hash_algo *);
+char *sha1_to_hex_r(char *out, const unsigned char *sha1);
+char *oid_to_hex_r(char *out, const struct object_id *oid);
+char *hash_to_hex_algop(const unsigned char *hash, const struct git_hash_algo *); /* static buffer result! */
+char *sha1_to_hex(const unsigned char *sha1); /* same static buffer */
+char *hash_to_hex(const unsigned char *hash); /* same static buffer */
+char *oid_to_hex(const struct object_id *oid); /* same static buffer */
/*
* Parse a 40-character hexadecimal object ID starting from hex, updating the
diff --git a/hex.c b/hex.c
index 10af1a29e8..7850a8879d 100644
--- a/hex.c
+++ b/hex.c
@@ -73,14 +73,15 @@ int parse_oid_hex(const char *hex, struct object_id *oid, const char **end)
return ret;
}
-char *sha1_to_hex_r(char *buffer, const unsigned char *sha1)
+char *hash_to_hex_algop_r(char *buffer, const unsigned char *hash,
+ const struct git_hash_algo *algop)
{
static const char hex[] = "0123456789abcdef";
char *buf = buffer;
int i;
- for (i = 0; i < the_hash_algo->rawsz; i++) {
- unsigned int val = *sha1++;
+ for (i = 0; i < algop->rawsz; i++) {
+ unsigned int val = *hash++;
*buf++ = hex[val >> 4];
*buf++ = hex[val & 0xf];
}
@@ -89,20 +90,35 @@ char *sha1_to_hex_r(char *buffer, const unsigned char *sha1)
return buffer;
}
-char *oid_to_hex_r(char *buffer, const struct object_id *oid)
+char *sha1_to_hex_r(char *buffer, const unsigned char *sha1)
{
- return sha1_to_hex_r(buffer, oid->hash);
+ return hash_to_hex_algop_r(buffer, sha1, &hash_algos[GIT_HASH_SHA1]);
}
-char *sha1_to_hex(const unsigned char *sha1)
+char *oid_to_hex_r(char *buffer, const struct object_id *oid)
+{
+ return hash_to_hex_algop_r(buffer, oid->hash, the_hash_algo);
+}
+
+char *hash_to_hex_algop(const unsigned char *hash, const struct git_hash_algo *algop)
{
static int bufno;
static char hexbuffer[4][GIT_MAX_HEXSZ + 1];
bufno = (bufno + 1) % ARRAY_SIZE(hexbuffer);
- return sha1_to_hex_r(hexbuffer[bufno], sha1);
+ return hash_to_hex_algop_r(hexbuffer[bufno], hash, algop);
+}
+
+char *sha1_to_hex(const unsigned char *sha1)
+{
+ return hash_to_hex_algop(sha1, &hash_algos[GIT_HASH_SHA1]);
+}
+
+char *hash_to_hex(const unsigned char *hash)
+{
+ return hash_to_hex_algop(hash, the_hash_algo);
}
char *oid_to_hex(const struct object_id *oid)
{
- return sha1_to_hex(oid->hash);
+ return hash_to_hex_algop(oid->hash, the_hash_algo);
}
From 0dab7129ab122d7ac5249fc7f6890302f29cd9e7 Mon Sep 17 00:00:00 2001
From: "brian m. carlson" <sandals@crustytoothpaste.net>
Date: Wed, 14 Nov 2018 04:09:30 +0000
Subject: [PATCH 04/12] cache: make hashcmp and hasheq work with larger hashes
In 183a638b7d ("hashcmp: assert constant hash size", 2018-08-23), we
modified hashcmp to assert that the hash size was always 20 to help it
optimize and inline calls to memcmp. In a future series, we replaced
many calls to hashcmp and oidcmp with calls to hasheq and oideq to
improve inlining further.
However, we want to support hash algorithms other than SHA-1, namely
SHA-256. When doing so, we must handle the case where these values are
32 bytes long as well as 20. Adjust hashcmp to handle two cases:
20-byte matches, and maximum-size matches. Therefore, when we include
SHA-256, we'll automatically handle it properly, while at the same time
teaching the compiler that there are only two possible options to
consider. This will allow the compiler to write the most efficient
possible code.
Copy similar code into hasheq and perform an identical transformation.
At least with GCC 8.2.0, making hasheq defer to hashcmp when there are
two branches prevents the compiler from inlining the comparison, while
the code in this patch is inlined properly. Add a comment to avoid an
accidental performance regression from well-intentioned refactoring.
Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
cache.h | 22 ++++++++++++----------
1 file changed, 12 insertions(+), 10 deletions(-)
diff --git a/cache.h b/cache.h
index 2ead61f05a..85a8e7b101 100644
--- a/cache.h
+++ b/cache.h
@@ -1024,16 +1024,12 @@ extern const struct object_id null_oid;
static inline int hashcmp(const unsigned char *sha1, const unsigned char *sha2)
{
/*
- * This is a temporary optimization hack. By asserting the size here,
- * we let the compiler know that it's always going to be 20, which lets
- * it turn this fixed-size memcmp into a few inline instructions.
- *
- * This will need to be extended or ripped out when we learn about
- * hashes of different sizes.
+ * Teach the compiler that there are only two possibilities of hash size
+ * here, so that it can optimize for this case as much as possible.
*/
- if (the_hash_algo->rawsz != 20)
- BUG("hash size not yet supported by hashcmp");
- return memcmp(sha1, sha2, the_hash_algo->rawsz);
+ if (the_hash_algo->rawsz == GIT_MAX_RAWSZ)
+ return memcmp(sha1, sha2, GIT_MAX_RAWSZ);
+ return memcmp(sha1, sha2, GIT_SHA1_RAWSZ);
}
static inline int oidcmp(const struct object_id *oid1, const struct object_id *oid2)
@@ -1043,7 +1039,13 @@ static inline int oidcmp(const struct object_id *oid1, const struct object_id *o
static inline int hasheq(const unsigned char *sha1, const unsigned char *sha2)
{
- return !hashcmp(sha1, sha2);
+ /*
+ * We write this here instead of deferring to hashcmp so that the
+ * compiler can properly inline it and avoid calling memcmp.
+ */
+ if (the_hash_algo->rawsz == GIT_MAX_RAWSZ)
+ return !memcmp(sha1, sha2, GIT_MAX_RAWSZ);
+ return !memcmp(sha1, sha2, GIT_SHA1_RAWSZ);
}
static inline int oideq(const struct object_id *oid1, const struct object_id *oid2)
From 9a3a0ff5374f07d60eea01bbbe9a399d1f325280 Mon Sep 17 00:00:00 2001
From: "brian m. carlson" <sandals@crustytoothpaste.net>
Date: Wed, 14 Nov 2018 04:09:31 +0000
Subject: [PATCH 05/12] t: add basic tests for our SHA-1 implementation
We have in the past had some unfortunate endianness issues with some
SHA-1 implementations we ship, especially on big-endian machines. Add
an explicit test using the test helper to catch these issues and point
them out prominently. This test can also be used as a staging ground
for people testing additional algorithms to verify that their
implementations are working as expected.
Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
t/t0015-hash.sh | 29 +++++++++++++++++++++++++++++
1 file changed, 29 insertions(+)
create mode 100755 t/t0015-hash.sh
diff --git a/t/t0015-hash.sh b/t/t0015-hash.sh
new file mode 100755
index 0000000000..884fe5acd1
--- /dev/null
+++ b/t/t0015-hash.sh
@@ -0,0 +1,29 @@
+#!/bin/sh
+
+test_description='test basic hash implementation'
+. ./test-lib.sh
+
+
+test_expect_success 'test basic SHA-1 hash values' '
+ test-tool sha1 </dev/null >actual &&
+ grep da39a3ee5e6b4b0d3255bfef95601890afd80709 actual &&
+ printf "a" | test-tool sha1 >actual &&
+ grep 86f7e437faa5a7fce15d1ddcb9eaeaea377667b8 actual &&
+ printf "abc" | test-tool sha1 >actual &&
+ grep a9993e364706816aba3e25717850c26c9cd0d89d actual &&
+ printf "message digest" | test-tool sha1 >actual &&
+ grep c12252ceda8be8994d5fa0290a47231c1d16aae3 actual &&
+ printf "abcdefghijklmnopqrstuvwxyz" | test-tool sha1 >actual &&
+ grep 32d10c7b8cf96570ca04ce37f2a19d84240d3a89 actual &&
+ perl -e "$| = 1; print q{aaaaaaaaaa} for 1..100000;" | \
+ test-tool sha1 >actual &&
+ grep 34aa973cd4c4daa4f61eeb2bdbad27316534016f actual &&
+ printf "blob 0\0" | test-tool sha1 >actual &&
+ grep e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 actual &&
+ printf "blob 3\0abc" | test-tool sha1 >actual &&
+ grep f2ba8f84ab5c1bce84a7b441cb1959cfc7093b7f actual &&
+ printf "tree 0\0" | test-tool sha1 >actual &&
+ grep 4b825dc642cb6eb9a060e54bf8d69288fbee4904 actual
+'
+
+test_done
From 50c817e0c02a133a1615ba32971fd5f6649c894f Mon Sep 17 00:00:00 2001
From: "brian m. carlson" <sandals@crustytoothpaste.net>
Date: Wed, 14 Nov 2018 04:09:32 +0000
Subject: [PATCH 06/12] t: make the sha1 test-tool helper generic
Since we're going to have multiple hash algorithms to test, it makes
sense to share as much of the test code as possible. Convert the sha1
helper for the test-tool to be generic and move it out into its own
module. This will allow us to share most of this code with our NewHash
implementation.
Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
Makefile | 1 +
t/helper/test-hash.c | 58 ++++++++++++++++++++++++++++++++++++++++++++
t/helper/test-sha1.c | 52 +--------------------------------------
t/helper/test-tool.h | 2 ++
4 files changed, 62 insertions(+), 51 deletions(-)
create mode 100644 t/helper/test-hash.c
diff --git a/Makefile b/Makefile
index 5c8307b7c4..324967410d 100644
--- a/Makefile
+++ b/Makefile
@@ -714,6 +714,7 @@ TEST_BUILTINS_OBJS += test-dump-split-index.o
TEST_BUILTINS_OBJS += test-dump-untracked-cache.o
TEST_BUILTINS_OBJS += test-example-decorate.o
TEST_BUILTINS_OBJS += test-genrandom.o
+TEST_BUILTINS_OBJS += test-hash.o
TEST_BUILTINS_OBJS += test-hashmap.o
TEST_BUILTINS_OBJS += test-index-version.o
TEST_BUILTINS_OBJS += test-json-writer.o
diff --git a/t/helper/test-hash.c b/t/helper/test-hash.c
new file mode 100644
index 0000000000..0a31de66f3
--- /dev/null
+++ b/t/helper/test-hash.c
@@ -0,0 +1,58 @@
+#include "test-tool.h"
+#include "cache.h"
+
+int cmd_hash_impl(int ac, const char **av, int algo)
+{
+ git_hash_ctx ctx;
+ unsigned char hash[GIT_MAX_HEXSZ];
+ unsigned bufsz = 8192;
+ int binary = 0;
+ char *buffer;
+ const struct git_hash_algo *algop = &hash_algos[algo];
+
+ if (ac == 2) {
+ if (!strcmp(av[1], "-b"))
+ binary = 1;
+ else
+ bufsz = strtoul(av[1], NULL, 10) * 1024 * 1024;
+ }
+
+ if (!bufsz)
+ bufsz = 8192;
+
+ while ((buffer = malloc(bufsz)) == NULL) {
+ fprintf(stderr, "bufsz %u is too big, halving...\n", bufsz);
+ bufsz /= 2;
+ if (bufsz < 1024)
+ die("OOPS");
+ }
+
+ algop->init_fn(&ctx);
+
+ while (1) {
+ ssize_t sz, this_sz;
+ char *cp = buffer;
+ unsigned room = bufsz;
+ this_sz = 0;
+ while (room) {
+ sz = xread(0, cp, room);
+ if (sz == 0)
+ break;
+ if (sz < 0)
+ die_errno("test-hash");
+ this_sz += sz;
+ cp += sz;
+ room -= sz;
+ }
+ if (this_sz == 0)
+ break;
+ algop->update_fn(&ctx, buffer, this_sz);
+ }
+ algop->final_fn(hash, &ctx);
+
+ if (binary)
+ fwrite(hash, 1, algop->rawsz, stdout);
+ else
+ puts(hash_to_hex_algop(hash, algop));
+ exit(0);
+}
diff --git a/t/helper/test-sha1.c b/t/helper/test-sha1.c
index 1ba0675c75..d860c387c3 100644
--- a/t/helper/test-sha1.c
+++ b/t/helper/test-sha1.c
@@ -3,55 +3,5 @@
int cmd__sha1(int ac, const char **av)
{
- git_SHA_CTX ctx;
- unsigned char sha1[20];
- unsigned bufsz = 8192;
- int binary = 0;
- char *buffer;
-
- if (ac == 2) {
- if (!strcmp(av[1], "-b"))
- binary = 1;
- else
- bufsz = strtoul(av[1], NULL, 10) * 1024 * 1024;
- }
-
- if (!bufsz)
- bufsz = 8192;
-
- while ((buffer = malloc(bufsz)) == NULL) {
- fprintf(stderr, "bufsz %u is too big, halving...\n", bufsz);
- bufsz /= 2;
- if (bufsz < 1024)
- die("OOPS");
- }
-
- git_SHA1_Init(&ctx);
-
- while (1) {
- ssize_t sz, this_sz;
- char *cp = buffer;
- unsigned room = bufsz;
- this_sz = 0;
- while (room) {
- sz = xread(0, cp, room);
- if (sz == 0)
- break;
- if (sz < 0)
- die_errno("test-sha1");
- this_sz += sz;
- cp += sz;
- room -= sz;
- }
- if (this_sz == 0)
- break;
- git_SHA1_Update(&ctx, buffer, this_sz);
- }
- git_SHA1_Final(sha1, &ctx);
-
- if (binary)
- fwrite(sha1, 1, 20, stdout);
- else
- puts(sha1_to_hex(sha1));
- exit(0);
+ return cmd_hash_impl(ac, av, GIT_HASH_SHA1);
}
diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h
index e4890566da..29ac7b0b0d 100644
--- a/t/helper/test-tool.h
+++ b/t/helper/test-tool.h
@@ -50,4 +50,6 @@ int cmd__windows_named_pipe(int argc, const char **argv);
#endif
int cmd__write_cache(int argc, const char **argv);
+int cmd_hash_impl(int ac, const char **av, int algo);
+
#endif
From a2ce0a752600a44979da94b19aa1b367c6850bd7 Mon Sep 17 00:00:00 2001
From: "brian m. carlson" <sandals@crustytoothpaste.net>
Date: Wed, 14 Nov 2018 04:09:33 +0000
Subject: [PATCH 07/12] sha1-file: add a constant for hash block size
There is one place we need the hash algorithm block size: the HMAC code
for push certs. Expose this constant in struct git_hash_algo and expose
values for SHA-1 and for the largest value of any hash.
Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
cache.h | 4 ++++
hash.h | 3 +++
sha1-file.c | 2 ++
3 files changed, 9 insertions(+)
diff --git a/cache.h b/cache.h
index 85a8e7b101..5d969727f9 100644
--- a/cache.h
+++ b/cache.h
@@ -45,10 +45,14 @@ unsigned long git_deflate_bound(git_zstream *, unsigned long);
/* The length in bytes and in hex digits of an object name (SHA-1 value). */
#define GIT_SHA1_RAWSZ 20
#define GIT_SHA1_HEXSZ (2 * GIT_SHA1_RAWSZ)
+/* The block size of SHA-1. */
+#define GIT_SHA1_BLKSZ 64
/* The length in byte and in hex digits of the largest possible hash value. */
#define GIT_MAX_RAWSZ GIT_SHA1_RAWSZ
#define GIT_MAX_HEXSZ GIT_SHA1_HEXSZ
+/* The largest possible block size for any supported hash. */
+#define GIT_MAX_BLKSZ GIT_SHA1_BLKSZ
struct object_id {
unsigned char hash[GIT_MAX_RAWSZ];
diff --git a/hash.h b/hash.h
index 80881eea47..1bcf7ab6fd 100644
--- a/hash.h
+++ b/hash.h
@@ -81,6 +81,9 @@ struct git_hash_algo {
/* The length of the hash in hex characters. */
size_t hexsz;
+ /* The block size of the hash. */
+ size_t blksz;
+
/* The hash initialization function. */
git_hash_init_fn init_fn;
diff --git a/sha1-file.c b/sha1-file.c
index 3a75d515eb..9aadaf0c8d 100644
--- a/sha1-file.c
+++ b/sha1-file.c
@@ -90,6 +90,7 @@ const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = {
0x00000000,
0,
0,
+ 0,
git_hash_unknown_init,
git_hash_unknown_update,
git_hash_unknown_final,
@@ -102,6 +103,7 @@ const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = {
0x73686131,
GIT_SHA1_RAWSZ,
GIT_SHA1_HEXSZ,
+ GIT_SHA1_BLKSZ,
git_hash_sha1_init,
git_hash_sha1_update,
git_hash_sha1_final,
From 37649b7f809f14b78d178c32e4d8333243f1f74e Mon Sep 17 00:00:00 2001
From: "brian m. carlson" <sandals@crustytoothpaste.net>
Date: Wed, 14 Nov 2018 04:09:34 +0000
Subject: [PATCH 08/12] t/helper: add a test helper to compute hash speed
Add a utility (which is less for the testsuite and more for developers)
that can compute hash speeds for whatever hash algorithms are
implemented. This allows developers to test their personal systems to
determine the performance characteristics of various algorithms.
Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
Makefile | 1 +
t/helper/test-hash-speed.c | 61 ++++++++++++++++++++++++++++++++++++++
t/helper/test-tool.c | 1 +
t/helper/test-tool.h | 1 +
4 files changed, 64 insertions(+)
create mode 100644 t/helper/test-hash-speed.c
diff --git a/Makefile b/Makefile
index 324967410d..1c43bf9aa8 100644
--- a/Makefile
+++ b/Makefile
@@ -716,6 +716,7 @@ TEST_BUILTINS_OBJS += test-example-decorate.o
TEST_BUILTINS_OBJS += test-genrandom.o
TEST_BUILTINS_OBJS += test-hash.o
TEST_BUILTINS_OBJS += test-hashmap.o
+TEST_BUILTINS_OBJS += test-hash-speed.o
TEST_BUILTINS_OBJS += test-index-version.o
TEST_BUILTINS_OBJS += test-json-writer.o
TEST_BUILTINS_OBJS += test-lazy-init-name-hash.o
diff --git a/t/helper/test-hash-speed.c b/t/helper/test-hash-speed.c
new file mode 100644
index 0000000000..432233c7f0
--- /dev/null
+++ b/t/helper/test-hash-speed.c
@@ -0,0 +1,61 @@
+#include "test-tool.h"
+#include "cache.h"
+
+#define NUM_SECONDS 3
+
+static inline void compute_hash(const struct git_hash_algo *algo, git_hash_ctx *ctx, uint8_t *final, const void *p, size_t len)
+{
+ algo->init_fn(ctx);
+ algo->update_fn(ctx, p, len);
+ algo->final_fn(final, ctx);
+}
+
+int cmd__hash_speed(int ac, const char **av)
+{
+ git_hash_ctx ctx;
+ unsigned char hash[GIT_MAX_RAWSZ];
+ clock_t initial, start, end;
+ unsigned bufsizes[] = { 64, 256, 1024, 8192, 16384 };
+ int i;
+ void *p;
+ const struct git_hash_algo *algo = NULL;
+
+ if (ac == 2) {
+ for (i = 1; i < GIT_HASH_NALGOS; i++) {
+ if (!strcmp(av[1], hash_algos[i].name)) {
+ algo = &hash_algos[i];
+ break;
+ }
+ }
+ }
+ if (!algo)
+ die("usage: test-tool hash-speed algo_name");
+
+ /* Use this as an offset to make overflow less likely. */
+ initial = clock();
+
+ printf("algo: %s\n", algo->name);
+
+ for (i = 0; i < ARRAY_SIZE(bufsizes); i++) {
+ unsigned long j, kb;
+ double kb_per_sec;
+ p = xcalloc(1, bufsizes[i]);
+ start = end = clock() - initial;
+ for (j = 0; ((end - start) / CLOCKS_PER_SEC) < NUM_SECONDS; j++) {
+ compute_hash(algo, &ctx, hash, p, bufsizes[i]);
+
+ /*
+ * Only check elapsed time every 128 iterations to avoid
+ * dominating the runtime with system calls.
+ */
+ if (!(j & 127))
+ end = clock() - initial;
+ }
+ kb = j * bufsizes[i];
+ kb_per_sec = kb / (1024 * ((double)end - start) / CLOCKS_PER_SEC);
+ printf("size %u: %lu iters; %lu KiB; %0.2f KiB/s\n", bufsizes[i], j, kb, kb_per_sec);
+ free(p);
+ }
+
+ exit(0);
+}
diff --git a/t/helper/test-tool.c b/t/helper/test-tool.c
index 6b5836dc1b..e009c8186d 100644
--- a/t/helper/test-tool.c
+++ b/t/helper/test-tool.c
@@ -20,6 +20,7 @@ static struct test_cmd cmds[] = {
{ "example-decorate", cmd__example_decorate },
{ "genrandom", cmd__genrandom },
{ "hashmap", cmd__hashmap },
+ { "hash-speed", cmd__hash_speed },
{ "index-version", cmd__index_version },
{ "json-writer", cmd__json_writer },
{ "lazy-init-name-hash", cmd__lazy_init_name_hash },
diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h
index 29ac7b0b0d..19a7e8332a 100644
--- a/t/helper/test-tool.h
+++ b/t/helper/test-tool.h
@@ -16,6 +16,7 @@ int cmd__dump_untracked_cache(int argc, const char **argv);
int cmd__example_decorate(int argc, const char **argv);
int cmd__genrandom(int argc, const char **argv);
int cmd__hashmap(int argc, const char **argv);
+int cmd__hash_speed(int argc, const char **argv);
int cmd__index_version(int argc, const char **argv);
int cmd__json_writer(int argc, const char **argv);
int cmd__lazy_init_name_hash(int argc, const char **argv);
From c166599862d10a273f61b834559eaa567c3dbfd9 Mon Sep 17 00:00:00 2001
From: "brian m. carlson" <sandals@crustytoothpaste.net>
Date: Wed, 14 Nov 2018 04:09:35 +0000
Subject: [PATCH 09/12] commit-graph: convert to using the_hash_algo
Instead of using hard-coded constants for object sizes, use
the_hash_algo to look them up. In addition, use a function call to look
up the object ID version and produce the correct value. For now, we use
version 1, which means to use the default algorithm used in the rest of
the repository.
Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
commit-graph.c | 33 +++++++++++++++++----------------
1 file changed, 17 insertions(+), 16 deletions(-)
diff --git a/commit-graph.c b/commit-graph.c
index 7f4519ec3b..7a28fbb03f 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -20,16 +20,11 @@
#define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */
#define GRAPH_CHUNKID_LARGEEDGES 0x45444745 /* "EDGE" */
-#define GRAPH_DATA_WIDTH 36
+#define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
#define GRAPH_VERSION_1 0x1
#define GRAPH_VERSION GRAPH_VERSION_1
-#define GRAPH_OID_VERSION_SHA1 1
-#define GRAPH_OID_LEN_SHA1 GIT_SHA1_RAWSZ
-#define GRAPH_OID_VERSION GRAPH_OID_VERSION_SHA1
-#define GRAPH_OID_LEN GRAPH_OID_LEN_SHA1
-
#define GRAPH_OCTOPUS_EDGES_NEEDED 0x80000000
#define GRAPH_PARENT_MISSING 0x7fffffff
#define GRAPH_EDGE_LAST_MASK 0x7fffffff
@@ -41,13 +36,18 @@
#define GRAPH_FANOUT_SIZE (4 * 256)
#define GRAPH_CHUNKLOOKUP_WIDTH 12
#define GRAPH_MIN_SIZE (GRAPH_HEADER_SIZE + 4 * GRAPH_CHUNKLOOKUP_WIDTH \
- + GRAPH_FANOUT_SIZE + GRAPH_OID_LEN)
+ + GRAPH_FANOUT_SIZE + the_hash_algo->rawsz)
char *get_commit_graph_filename(const char *obj_dir)
{
return xstrfmt("%s/info/commit-graph", obj_dir);
}
+static uint8_t oid_version(void)
+{
+ return 1;
+}
+
static struct commit_graph *alloc_commit_graph(void)
{
struct commit_graph *g = xcalloc(1, sizeof(*g));
@@ -100,15 +100,15 @@ struct commit_graph *load_commit_graph_one(const char *graph_file)
}
hash_version = *(unsigned char*)(data + 5);
- if (hash_version != GRAPH_OID_VERSION) {
+ if (hash_version != oid_version()) {
error(_("hash version %X does not match version %X"),
- hash_version, GRAPH_OID_VERSION);
+ hash_version, oid_version());
goto cleanup_fail;
}
graph = alloc_commit_graph();
- graph->hash_len = GRAPH_OID_LEN;
+ graph->hash_len = the_hash_algo->rawsz;
graph->num_chunks = *(unsigned char*)(data + 6);
graph->graph_fd = fd;
graph->data = graph_map;
@@ -124,7 +124,7 @@ struct commit_graph *load_commit_graph_one(const char *graph_file)
chunk_lookup += GRAPH_CHUNKLOOKUP_WIDTH;
- if (chunk_offset > graph_size - GIT_MAX_RAWSZ) {
+ if (chunk_offset > graph_size - the_hash_algo->rawsz) {
error(_("improper chunk offset %08x%08x"), (uint32_t)(chunk_offset >> 32),
(uint32_t)chunk_offset);
goto cleanup_fail;
@@ -711,6 +711,7 @@ void write_commit_graph(const char *obj_dir,
int num_chunks;
int num_extra_edges;
struct commit_list *parent;
+ const unsigned hashsz = the_hash_algo->rawsz;
oids.nr = 0;
oids.alloc = approximate_object_count() / 4;
@@ -831,7 +832,7 @@ void write_commit_graph(const char *obj_dir,
hashwrite_be32(f, GRAPH_SIGNATURE);
hashwrite_u8(f, GRAPH_VERSION);
- hashwrite_u8(f, GRAPH_OID_VERSION);
+ hashwrite_u8(f, oid_version());
hashwrite_u8(f, num_chunks);
hashwrite_u8(f, 0); /* unused padding byte */
@@ -846,8 +847,8 @@ void write_commit_graph(const char *obj_dir,
chunk_offsets[0] = 8 + (num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH;
chunk_offsets[1] = chunk_offsets[0] + GRAPH_FANOUT_SIZE;
- chunk_offsets[2] = chunk_offsets[1] + GRAPH_OID_LEN * commits.nr;
- chunk_offsets[3] = chunk_offsets[2] + (GRAPH_OID_LEN + 16) * commits.nr;
+ chunk_offsets[2] = chunk_offsets[1] + hashsz * commits.nr;
+ chunk_offsets[3] = chunk_offsets[2] + (hashsz + 16) * commits.nr;
chunk_offsets[4] = chunk_offsets[3] + 4 * num_extra_edges;
for (i = 0; i <= num_chunks; i++) {
@@ -860,8 +861,8 @@ void write_commit_graph(const char *obj_dir,
}
write_graph_chunk_fanout(f, commits.list, commits.nr);
- write_graph_chunk_oids(f, GRAPH_OID_LEN, commits.list, commits.nr);
- write_graph_chunk_data(f, GRAPH_OID_LEN, commits.list, commits.nr);
+ write_graph_chunk_oids(f, hashsz, commits.list, commits.nr);
+ write_graph_chunk_data(f, hashsz, commits.list, commits.nr);
write_graph_chunk_large_edges(f, commits.list, commits.nr);
close_commit_graph();
From 13eeedb5d17ca3539600b6618d103b652ecc8ab0 Mon Sep 17 00:00:00 2001
From: "brian m. carlson" <sandals@crustytoothpaste.net>
Date: Wed, 14 Nov 2018 04:09:36 +0000
Subject: [PATCH 10/12] Add a base implementation of SHA-256 support
SHA-1 is weak and we need to transition to a new hash function. For
some time, we have referred to this new function as NewHash. Recently,
we decided to pick SHA-256 as NewHash. The reasons behind the choice of
SHA-256 are outlined in the thread starting at [1] and in the commit
history for the hash function transition document.
Add a basic implementation of SHA-256 based off libtomcrypt, which is in
the public domain. Optimize it and restructure it to meet our coding
standards. Pull in the update and final functions from the SHA-1 block
implementation, as we know these function correctly with all compilers.
This implementation is slower than SHA-1, but more performant
implementations will be introduced in future commits.
Wire up SHA-256 in the list of hash algorithms, and add a test that the
algorithm works correctly.
Note that with this patch, it is still not possible to switch to using
SHA-256 in Git. Additional patches are needed to prepare the code to
handle a larger hash algorithm and further test fixes are needed.
[1] https://public-inbox.org/git/20180609224913.GC38834@genre.crustytoothpaste.net/
Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
Makefile | 4 +
cache.h | 12 ++-
hash.h | 19 +++-
sha1-file.c | 45 ++++++++++
sha256/block/sha256.c | 196 +++++++++++++++++++++++++++++++++++++++++
sha256/block/sha256.h | 24 +++++
t/helper/test-sha256.c | 7 ++
t/helper/test-tool.c | 1 +
t/helper/test-tool.h | 1 +
t/t0015-hash.sh | 26 ++++++
10 files changed, 331 insertions(+), 4 deletions(-)
create mode 100644 sha256/block/sha256.c
create mode 100644 sha256/block/sha256.h
create mode 100644 t/helper/test-sha256.c
diff --git a/Makefile b/Makefile
index 1c43bf9aa8..76d378c7ba 100644
--- a/Makefile
+++ b/Makefile
@@ -739,6 +739,7 @@ TEST_BUILTINS_OBJS += test-run-command.o
TEST_BUILTINS_OBJS += test-scrap-cache-tree.o
TEST_BUILTINS_OBJS += test-sha1.o
TEST_BUILTINS_OBJS += test-sha1-array.o
+TEST_BUILTINS_OBJS += test-sha256.o
TEST_BUILTINS_OBJS += test-sigchain.o
TEST_BUILTINS_OBJS += test-strcmp-offset.o
TEST_BUILTINS_OBJS += test-string-list.o
@@ -1633,6 +1634,9 @@ endif
endif
endif
+LIB_OBJS += sha256/block/sha256.o
+BASIC_CFLAGS += -DSHA256_BLK
+
ifdef SHA1_MAX_BLOCK_SIZE
LIB_OBJS += compat/sha1-chunked.o
BASIC_CFLAGS += -DSHA1_MAX_BLOCK_SIZE="$(SHA1_MAX_BLOCK_SIZE)"
diff --git a/cache.h b/cache.h
index 5d969727f9..a082164df8 100644
--- a/cache.h
+++ b/cache.h
@@ -48,11 +48,17 @@ unsigned long git_deflate_bound(git_zstream *, unsigned long);
/* The block size of SHA-1. */
#define GIT_SHA1_BLKSZ 64
+/* The length in bytes and in hex digits of an object name (SHA-256 value). */
+#define GIT_SHA256_RAWSZ 32
+#define GIT_SHA256_HEXSZ (2 * GIT_SHA256_RAWSZ)
+/* The block size of SHA-256. */
+#define GIT_SHA256_BLKSZ 64
+
/* The length in byte and in hex digits of the largest possible hash value. */
-#define GIT_MAX_RAWSZ GIT_SHA1_RAWSZ
-#define GIT_MAX_HEXSZ GIT_SHA1_HEXSZ
+#define GIT_MAX_RAWSZ GIT_SHA256_RAWSZ
+#define GIT_MAX_HEXSZ GIT_SHA256_HEXSZ
/* The largest possible block size for any supported hash. */
-#define GIT_MAX_BLKSZ GIT_SHA1_BLKSZ
+#define GIT_MAX_BLKSZ GIT_SHA256_BLKSZ
struct object_id {
unsigned char hash[GIT_MAX_RAWSZ];
diff --git a/hash.h b/hash.h
index 1bcf7ab6fd..a9bc624020 100644
--- a/hash.h
+++ b/hash.h
@@ -15,6 +15,8 @@
#include "block-sha1/sha1.h"
#endif
+#include "sha256/block/sha256.h"
+
#ifndef platform_SHA_CTX
/*
* platform's underlying implementation of SHA-1; could be OpenSSL,
@@ -34,6 +36,18 @@
#define git_SHA1_Update platform_SHA1_Update
#define git_SHA1_Final platform_SHA1_Final
+#ifndef platform_SHA256_CTX
+#define platform_SHA256_CTX SHA256_CTX
+#define platform_SHA256_Init SHA256_Init
+#define platform_SHA256_Update SHA256_Update
+#define platform_SHA256_Final SHA256_Final
+#endif
+
+#define git_SHA256_CTX platform_SHA256_CTX
+#define git_SHA256_Init platform_SHA256_Init
+#define git_SHA256_Update platform_SHA256_Update
+#define git_SHA256_Final platform_SHA256_Final
+
#ifdef SHA1_MAX_BLOCK_SIZE
#include "compat/sha1-chunked.h"
#undef git_SHA1_Update
@@ -52,12 +66,15 @@
#define GIT_HASH_UNKNOWN 0
/* SHA-1 */
#define GIT_HASH_SHA1 1
+/* SHA-256 */
+#define GIT_HASH_SHA256 2
/* Number of algorithms supported (including unknown). */
-#define GIT_HASH_NALGOS (GIT_HASH_SHA1 + 1)
+#define GIT_HASH_NALGOS (GIT_HASH_SHA256 + 1)
/* A suitably aligned type for stack allocations of hash contexts. */
union git_hash_ctx {
git_SHA_CTX sha1;
+ git_SHA256_CTX sha256;
};
typedef union git_hash_ctx git_hash_ctx;
diff --git a/sha1-file.c b/sha1-file.c
index 9aadaf0c8d..66ba3dadb9 100644
--- a/sha1-file.c
+++ b/sha1-file.c
@@ -40,10 +40,20 @@
#define EMPTY_TREE_SHA1_BIN_LITERAL \
"\x4b\x82\x5d\xc6\x42\xcb\x6e\xb9\xa0\x60" \
"\xe5\x4b\xf8\xd6\x92\x88\xfb\xee\x49\x04"
+#define EMPTY_TREE_SHA256_BIN_LITERAL \
+ "\x6e\xf1\x9b\x41\x22\x5c\x53\x69\xf1\xc1" \
+ "\x04\xd4\x5d\x8d\x85\xef\xa9\xb0\x57\xb5" \
+ "\x3b\x14\xb4\xb9\xb9\x39\xdd\x74\xde\xcc" \
+ "\x53\x21"
#define EMPTY_BLOB_SHA1_BIN_LITERAL \
"\xe6\x9d\xe2\x9b\xb2\xd1\xd6\x43\x4b\x8b" \
"\x29\xae\x77\x5a\xd8\xc2\xe4\x8c\x53\x91"
+#define EMPTY_BLOB_SHA256_BIN_LITERAL \
+ "\x47\x3a\x0f\x4c\x3b\xe8\xa9\x36\x81\xa2" \
+ "\x67\xe3\xb1\xe9\xa7\xdc\xda\x11\x85\x43" \
+ "\x6f\xe1\x41\xf7\x74\x91\x20\xa3\x03\x72" \
+ "\x18\x13"
const unsigned char null_sha1[GIT_MAX_RAWSZ];
const struct object_id null_oid;
@@ -53,6 +63,12 @@ static const struct object_id empty_tree_oid = {
static const struct object_id empty_blob_oid = {
EMPTY_BLOB_SHA1_BIN_LITERAL
};
+static const struct object_id empty_tree_oid_sha256 = {
+ EMPTY_TREE_SHA256_BIN_LITERAL
+};
+static const struct object_id empty_blob_oid_sha256 = {
+ EMPTY_BLOB_SHA256_BIN_LITERAL
+};
static void git_hash_sha1_init(git_hash_ctx *ctx)
{
@@ -69,6 +85,22 @@ static void git_hash_sha1_final(unsigned char *hash, git_hash_ctx *ctx)
git_SHA1_Final(hash, &ctx->sha1);
}
+
+static void git_hash_sha256_init(git_hash_ctx *ctx)
+{
+ git_SHA256_Init(&ctx->sha256);
+}
+
+static void git_hash_sha256_update(git_hash_ctx *ctx, const void *data, size_t len)
+{
+ git_SHA256_Update(&ctx->sha256, data, len);
+}
+
+static void git_hash_sha256_final(unsigned char *hash, git_hash_ctx *ctx)
+{
+ git_SHA256_Final(hash, &ctx->sha256);
+}
+
static void git_hash_unknown_init(git_hash_ctx *ctx)
{
BUG("trying to init unknown hash");
@@ -110,6 +142,19 @@ const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = {
&empty_tree_oid,
&empty_blob_oid,
},
+ {
+ "sha256",
+ /* "s256", big-endian */
+ 0x73323536,
+ GIT_SHA256_RAWSZ,
+ GIT_SHA256_HEXSZ,
+ GIT_SHA256_BLKSZ,
+ git_hash_sha256_init,
+ git_hash_sha256_update,
+ git_hash_sha256_final,
+ &empty_tree_oid_sha256,
+ &empty_blob_oid_sha256,
+ }
};
const char *empty_tree_oid_hex(void)
diff --git a/sha256/block/sha256.c b/sha256/block/sha256.c
new file mode 100644
index 0000000000..37850b4e52
--- /dev/null
+++ b/sha256/block/sha256.c
@@ -0,0 +1,196 @@
+#include "git-compat-util.h"
+#include "./sha256.h"
+
+#undef RND
+#undef BLKSIZE
+
+#define BLKSIZE blk_SHA256_BLKSIZE
+
+void blk_SHA256_Init(blk_SHA256_CTX *ctx)
+{
+ ctx->offset = 0;
+ ctx->size = 0;
+ ctx->state[0] = 0x6a09e667ul;
+ ctx->state[1] = 0xbb67ae85ul;
+ ctx->state[2] = 0x3c6ef372ul;
+ ctx->state[3] = 0xa54ff53aul;
+ ctx->state[4] = 0x510e527ful;
+ ctx->state[5] = 0x9b05688cul;
+ ctx->state[6] = 0x1f83d9abul;
+ ctx->state[7] = 0x5be0cd19ul;
+}
+
+static inline uint32_t ror(uint32_t x, unsigned n)
+{
+ return (x >> n) | (x << (32 - n));
+}
+
+static inline uint32_t ch(uint32_t x, uint32_t y, uint32_t z)
+{
+ return z ^ (x & (y ^ z));
+}
+
+static inline uint32_t maj(uint32_t x, uint32_t y, uint32_t z)
+{
+ return ((x | y) & z) | (x & y);
+}
+
+static inline uint32_t sigma0(uint32_t x)
+{
+ return ror(x, 2) ^ ror(x, 13) ^ ror(x, 22);
+}
+
+static inline uint32_t sigma1(uint32_t x)
+{
+ return ror(x, 6) ^ ror(x, 11) ^ ror(x, 25);
+}
+
+static inline uint32_t gamma0(uint32_t x)
+{
+ return ror(x, 7) ^ ror(x, 18) ^ (x >> 3);
+}
+
+static inline uint32_t gamma1(uint32_t x)
+{
+ return ror(x, 17) ^ ror(x, 19) ^ (x >> 10);
+}
+
+static void blk_SHA256_Transform(blk_SHA256_CTX *ctx, const unsigned char *buf)
+{
+
+ uint32_t S[8], W[64], t0, t1;
+ int i;
+
+ /* copy state into S */
+ for (i = 0; i < 8; i++)
+ S[i] = ctx->state[i];
+
+ /* copy the state into 512-bits into W[0..15] */
+ for (i = 0; i < 16; i++, buf += sizeof(uint32_t))
+ W[i] = get_be32(buf);
+
+ /* fill W[16..63] */
+ for (i = 16; i < 64; i++)
+ W[i] = gamma1(W[i - 2]) + W[i - 7] + gamma0(W[i - 15]) + W[i - 16];
+
+#define RND(a,b,c,d,e,f,g,h,i,ki) \
+ t0 = h + sigma1(e) + ch(e, f, g) + ki + W[i]; \
+ t1 = sigma0(a) + maj(a, b, c); \
+ d += t0; \
+ h = t0 + t1;
+
+ RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],0,0x428a2f98);
+ RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],1,0x71374491);
+ RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],2,0xb5c0fbcf);
+ RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],3,0xe9b5dba5);
+ RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],4,0x3956c25b);
+ RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],5,0x59f111f1);
+ RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],6,0x923f82a4);
+ RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],7,0xab1c5ed5);
+ RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],8,0xd807aa98);
+ RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],9,0x12835b01);
+ RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],10,0x243185be);
+ RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],11,0x550c7dc3);
+ RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],12,0x72be5d74);
+ RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],13,0x80deb1fe);
+ RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],14,0x9bdc06a7);
+ RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],15,0xc19bf174);
+ RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],16,0xe49b69c1);
+ RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],17,0xefbe4786);
+ RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],18,0x0fc19dc6);
+ RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],19,0x240ca1cc);
+ RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],20,0x2de92c6f);
+ RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],21,0x4a7484aa);
+ RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],22,0x5cb0a9dc);
+ RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],23,0x76f988da);
+ RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],24,0x983e5152);
+ RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],25,0xa831c66d);
+ RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],26,0xb00327c8);
+ RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],27,0xbf597fc7);
+ RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],28,0xc6e00bf3);
+ RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],29,0xd5a79147);
+ RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],30,0x06ca6351);
+ RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],31,0x14292967);
+ RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],32,0x27b70a85);
+ RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],33,0x2e1b2138);
+ RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],34,0x4d2c6dfc);
+ RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],35,0x53380d13);
+ RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],36,0x650a7354);
+ RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],37,0x766a0abb);
+ RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],38,0x81c2c92e);
+ RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],39,0x92722c85);
+ RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],40,0xa2bfe8a1);
+ RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],41,0xa81a664b);
+ RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],42,0xc24b8b70);
+ RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],43,0xc76c51a3);
+ RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],44,0xd192e819);
+ RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],45,0xd6990624);
+ RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],46,0xf40e3585);
+ RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],47,0x106aa070);
+ RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],48,0x19a4c116);
+ RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],49,0x1e376c08);
+ RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],50,0x2748774c);
+ RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],51,0x34b0bcb5);
+ RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],52,0x391c0cb3);
+ RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],53,0x4ed8aa4a);
+ RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],54,0x5b9cca4f);
+ RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],55,0x682e6ff3);
+ RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],56,0x748f82ee);
+ RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],57,0x78a5636f);
+ RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],58,0x84c87814);
+ RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],59,0x8cc70208);
+ RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],60,0x90befffa);
+ RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],61,0xa4506ceb);
+ RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],62,0xbef9a3f7);
+ RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],63,0xc67178f2);
+
+ for (i = 0; i < 8; i++)
+ ctx->state[i] += S[i];
+}
+
+void blk_SHA256_Update(blk_SHA256_CTX *ctx, const void *data, size_t len)
+{
+ unsigned int len_buf = ctx->size & 63;
+
+ ctx->size += len;
+
+ /* Read the data into buf and process blocks as they get full */
+ if (len_buf) {
+ unsigned int left = 64 - len_buf;
+ if (len < left)
+ left = len;
+ memcpy(len_buf + ctx->buf, data, left);
+ len_buf = (len_buf + left) & 63;
+ len -= left;
+ data = ((const char *)data + left);
+ if (len_buf)
+ return;
+ blk_SHA256_Transform(ctx, ctx->buf);
+ }
+ while (len >= 64) {
+ blk_SHA256_Transform(ctx, data);
+ data = ((const char *)data + 64);
+ len -= 64;
+ }
+ if (len)
+ memcpy(ctx->buf, data, len);
+}
+
+void blk_SHA256_Final(unsigned char *digest, blk_SHA256_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;
+ blk_SHA256_Update(ctx, pad, 1 + (63 & (55 - i)));
+ blk_SHA256_Update(ctx, padlen, 8);
+
+ /* copy output */
+ for (i = 0; i < 8; i++, digest += sizeof(uint32_t))
+ put_be32(digest, ctx->state[i]);
+}
diff --git a/sha256/block/sha256.h b/sha256/block/sha256.h
new file mode 100644
index 0000000000..5099d6421d
--- /dev/null
+++ b/sha256/block/sha256.h
@@ -0,0 +1,24 @@
+#ifndef SHA256_BLOCK_SHA256_H
+#define SHA256_BLOCK_SHA256_H
+
+#define blk_SHA256_BLKSIZE 64
+
+struct blk_SHA256_CTX {
+ uint32_t state[8];
+ uint64_t size;
+ uint32_t offset;
+ uint8_t buf[blk_SHA256_BLKSIZE];
+};
+
+typedef struct blk_SHA256_CTX blk_SHA256_CTX;
+
+void blk_SHA256_Init(blk_SHA256_CTX *ctx);
+void blk_SHA256_Update(blk_SHA256_CTX *ctx, const void *data, size_t len);
+void blk_SHA256_Final(unsigned char *digest, blk_SHA256_CTX *ctx);
+
+#define platform_SHA256_CTX blk_SHA256_CTX
+#define platform_SHA256_Init blk_SHA256_Init
+#define platform_SHA256_Update blk_SHA256_Update
+#define platform_SHA256_Final blk_SHA256_Final
+
+#endif
diff --git a/t/helper/test-sha256.c b/t/helper/test-sha256.c
new file mode 100644
index 0000000000..0ac6a99d5f
--- /dev/null
+++ b/t/helper/test-sha256.c
@@ -0,0 +1,7 @@
+#include "test-tool.h"
+#include "cache.h"
+
+int cmd__sha256(int ac, const char **av)
+{
+ return cmd_hash_impl(ac, av, GIT_HASH_SHA256);
+}
diff --git a/t/helper/test-tool.c b/t/helper/test-tool.c
index e009c8186d..2a65193514 100644
--- a/t/helper/test-tool.c
+++ b/t/helper/test-tool.c
@@ -43,6 +43,7 @@ static struct test_cmd cmds[] = {
{ "scrap-cache-tree", cmd__scrap_cache_tree },
{ "sha1", cmd__sha1 },
{ "sha1-array", cmd__sha1_array },
+ { "sha256", cmd__sha256 },
{ "sigchain", cmd__sigchain },
{ "strcmp-offset", cmd__strcmp_offset },
{ "string-list", cmd__string_list },
diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h
index 19a7e8332a..2e66a8e47b 100644
--- a/t/helper/test-tool.h
+++ b/t/helper/test-tool.h
@@ -39,6 +39,7 @@ int cmd__run_command(int argc, const char **argv);
int cmd__scrap_cache_tree(int argc, const char **argv);
int cmd__sha1(int argc, const char **argv);
int cmd__sha1_array(int argc, const char **argv);
+int cmd__sha256(int argc, const char **argv);
int cmd__sigchain(int argc, const char **argv);
int cmd__strcmp_offset(int argc, const char **argv);
int cmd__string_list(int argc, const char **argv);
diff --git a/t/t0015-hash.sh b/t/t0015-hash.sh
index 884fe5acd1..291e9061f3 100755
--- a/t/t0015-hash.sh
+++ b/t/t0015-hash.sh
@@ -26,4 +26,30 @@ test_expect_success 'test basic SHA-1 hash values' '
grep 4b825dc642cb6eb9a060e54bf8d69288fbee4904 actual
'
+test_expect_success 'test basic SHA-256 hash values' '
+ test-tool sha256 </dev/null >actual &&
+ grep e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 actual &&
+ printf "a" | test-tool sha256 >actual &&
+ grep ca978112ca1bbdcafac231b39a23dc4da786eff8147c4e72b9807785afee48bb actual &&
+ printf "abc" | test-tool sha256 >actual &&
+ grep ba7816bf8f01cfea414140de5dae2223b00361a396177a9cb410ff61f20015ad actual &&
+ printf "message digest" | test-tool sha256 >actual &&
+ grep f7846f55cf23e14eebeab5b4e1550cad5b509e3348fbc4efa3a1413d393cb650 actual &&
+ printf "abcdefghijklmnopqrstuvwxyz" | test-tool sha256 >actual &&
+ grep 71c480df93d6ae2f1efad1447c66c9525e316218cf51fc8d9ed832f2daf18b73 actual &&
+ # Try to exercise the chunking code by turning autoflush on.
+ perl -e "$| = 1; print q{aaaaaaaaaa} for 1..100000;" | \
+ test-tool sha256 >actual &&
+ grep cdc76e5c9914fb9281a1c7e284d73e67f1809a48a497200e046d39ccc7112cd0 actual &&
+ perl -e "$| = 1; print q{abcdefghijklmnopqrstuvwxyz} for 1..100000;" | \
+ test-tool sha256 >actual &&
+ grep e406ba321ca712ad35a698bf0af8d61fc4dc40eca6bdcea4697962724ccbde35 actual &&
+ printf "blob 0\0" | test-tool sha256 >actual &&
+ grep 473a0f4c3be8a93681a267e3b1e9a7dcda1185436fe141f7749120a303721813 actual &&
+ printf "blob 3\0abc" | test-tool sha256 >actual &&
+ grep c1cf6e465077930e88dc5136641d402f72a229ddd996f627d60e9639eaba35a6 actual &&
+ printf "tree 0\0" | test-tool sha256 >actual &&
+ grep 6ef19b41225c5369f1c104d45d8d85efa9b057b53b14b4b9b939dd74decc5321 actual
+'
+
test_done
From 27dc04c54506967fcaa87b2d560547ee5633040c Mon Sep 17 00:00:00 2001
From: "brian m. carlson" <sandals@crustytoothpaste.net>
Date: Wed, 14 Nov 2018 04:09:37 +0000
Subject: [PATCH 11/12] sha256: add an SHA-256 implementation using libgcrypt
Generally, one gets better performance out of cryptographic routines
written in assembly than C, and this is also true for SHA-256. In
addition, most Linux distributions cannot distribute Git linked against
OpenSSL for licensing reasons.
Most systems with GnuPG will also have libgcrypt, since it is a
dependency of GnuPG. libgcrypt is also faster than the SHA1DC
implementation for messages of a few KiB and larger.
For comparison, on a Core i7-6600U, this implementation processes 16 KiB
chunks at 355 MiB/s while SHA1DC processes equivalent chunks at 337
MiB/s.
In addition, libgcrypt is licensed under the LGPL 2.1, which is
compatible with the GPL. Add an implementation of SHA-256 that uses
libgcrypt.
Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
Makefile | 13 +++++++++++--
hash.h | 4 ++++
sha256/gcrypt.h | 30 ++++++++++++++++++++++++++++++
3 files changed, 45 insertions(+), 2 deletions(-)
create mode 100644 sha256/gcrypt.h
diff --git a/Makefile b/Makefile
index 76d378c7ba..3d91555a81 100644
--- a/Makefile
+++ b/Makefile
@@ -179,6 +179,10 @@ all::
# in one call to the platform's SHA1_Update(). e.g. APPLE_COMMON_CRYPTO
# wants 'SHA1_MAX_BLOCK_SIZE=1024L*1024L*1024L' defined.
#
+# Define BLK_SHA256 to use the built-in SHA-256 routines.
+#
+# Define GCRYPT_SHA256 to use the SHA-256 routines in libgcrypt.
+#
# Define NEEDS_CRYPTO_WITH_SSL if you need -lcrypto when using -lssl (Darwin).
#
# Define NEEDS_SSL_WITH_CRYPTO if you need -lssl when using -lcrypto (Darwin).
@@ -1634,8 +1638,13 @@ endif
endif
endif
-LIB_OBJS += sha256/block/sha256.o
-BASIC_CFLAGS += -DSHA256_BLK
+ifdef GCRYPT_SHA256
+ BASIC_CFLAGS += -DSHA256_GCRYPT
+ EXTLIBS += -lgcrypt
+else
+ LIB_OBJS += sha256/block/sha256.o
+ BASIC_CFLAGS += -DSHA256_BLK
+endif
ifdef SHA1_MAX_BLOCK_SIZE
LIB_OBJS += compat/sha1-chunked.o
diff --git a/hash.h b/hash.h
index a9bc624020..2ef098052d 100644
--- a/hash.h
+++ b/hash.h
@@ -15,7 +15,11 @@
#include "block-sha1/sha1.h"
#endif
+#if defined(SHA256_GCRYPT)
+#include "sha256/gcrypt.h"
+#else
#include "sha256/block/sha256.h"
+#endif
#ifndef platform_SHA_CTX
/*
diff --git a/sha256/gcrypt.h b/sha256/gcrypt.h
new file mode 100644
index 0000000000..09bd8bb200
--- /dev/null
+++ b/sha256/gcrypt.h
@@ -0,0 +1,30 @@
+#ifndef SHA256_GCRYPT_H
+#define SHA256_GCRYPT_H
+
+#include <gcrypt.h>
+
+#define SHA256_DIGEST_SIZE 32
+
+typedef gcry_md_hd_t gcrypt_SHA256_CTX;
+
+inline void gcrypt_SHA256_Init(gcrypt_SHA256_CTX *ctx)
+{
+ gcry_md_open(ctx, GCRY_MD_SHA256, 0);
+}
+
+inline void gcrypt_SHA256_Update(gcrypt_SHA256_CTX *ctx, const void *data, size_t len)
+{
+ gcry_md_write(*ctx, data, len);
+}
+
+inline void gcrypt_SHA256_Final(unsigned char *digest, gcrypt_SHA256_CTX *ctx)
+{
+ memcpy(digest, gcry_md_read(*ctx, GCRY_MD_SHA256), SHA256_DIGEST_SIZE);
+}
+
+#define platform_SHA256_CTX gcrypt_SHA256_CTX
+#define platform_SHA256_Init gcrypt_SHA256_Init
+#define platform_SHA256_Update gcrypt_SHA256_Update
+#define platform_SHA256_Final gcrypt_SHA256_Final
+
+#endif
From 4b4e2918099600c1eefe7b5a71bf647803905b7e Mon Sep 17 00:00:00 2001
From: "brian m. carlson" <sandals@crustytoothpaste.net>
Date: Wed, 14 Nov 2018 04:09:38 +0000
Subject: [PATCH 12/12] hash: add an SHA-256 implementation using OpenSSL
We already have OpenSSL routines available for SHA-1, so add routines
for SHA-256 as well.
On a Core i7-6600U, this SHA-256 implementation compares favorably to
the SHA1DC SHA-1 implementation:
SHA-1: 157 MiB/s (64 byte chunks); 337 MiB/s (16 KiB chunks)
SHA-256: 165 MiB/s (64 byte chunks); 408 MiB/s (16 KiB chunks)
Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
Makefile | 7 +++++++
hash.h | 2 ++
2 files changed, 9 insertions(+)
diff --git a/Makefile b/Makefile
index 3d91555a81..3164e2aeee 100644
--- a/Makefile
+++ b/Makefile
@@ -183,6 +183,8 @@ all::
#
# Define GCRYPT_SHA256 to use the SHA-256 routines in libgcrypt.
#
+# Define OPENSSL_SHA256 to use the SHA-256 routines in OpenSSL.
+#
# Define NEEDS_CRYPTO_WITH_SSL if you need -lcrypto when using -lssl (Darwin).
#
# Define NEEDS_SSL_WITH_CRYPTO if you need -lssl when using -lcrypto (Darwin).
@@ -1638,6 +1640,10 @@ endif
endif
endif
+ifdef OPENSSL_SHA256
+ EXTLIBS += $(LIB_4_CRYPTO)
+ BASIC_CFLAGS += -DSHA256_OPENSSL
+else
ifdef GCRYPT_SHA256
BASIC_CFLAGS += -DSHA256_GCRYPT
EXTLIBS += -lgcrypt
@@ -1645,6 +1651,7 @@ else
LIB_OBJS += sha256/block/sha256.o
BASIC_CFLAGS += -DSHA256_BLK
endif
+endif
ifdef SHA1_MAX_BLOCK_SIZE
LIB_OBJS += compat/sha1-chunked.o
diff --git a/hash.h b/hash.h
index 2ef098052d..adde708cf2 100644
--- a/hash.h
+++ b/hash.h
@@ -17,6 +17,8 @@
#if defined(SHA256_GCRYPT)
#include "sha256/gcrypt.h"
+#elif defined(SHA256_OPENSSL)
+#include <openssl/sha.h>
#else
#include "sha256/block/sha256.h"
#endif