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/[email protected]/

Signed-off-by: brian m. carlson <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

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)"

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];

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;
 

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)

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]);
+}

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

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);
+}

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 },