Merge branch 'bc/sha-256'

Add sha-256 hash and plug it through the code to allow building Git
with the "NewHash".

* bc/sha-256:
  hash: add an SHA-256 implementation using OpenSSL
  sha256: add an SHA-256 implementation using libgcrypt
  Add a base implementation of SHA-256 support
  commit-graph: convert to using the_hash_algo
  t/helper: add a test helper to compute hash speed
  sha1-file: add a constant for hash block size
  t: make the sha1 test-tool helper generic
  t: add basic tests for our SHA-1 implementation
  cache: make hashcmp and hasheq work with larger hashes
  hex: introduce functions to print arbitrary hashes
  sha1-file: provide functions to look up hash algorithms
  sha1-file: rename algorithm to "sha1"

1 files changed, 33 insertions, 18 deletions

diff --git a/cache.h b/cache.h
index 49713cc..d94eff8 100644
--- a/cache.h
+++ b/cache.h
@@ -45,10 +45,20 @@ 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 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_SHA256_BLKSZ
 
 struct object_id {
 	unsigned char hash[GIT_MAX_RAWSZ];
@@ -1028,16 +1038,12 @@ 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)
@@ -1047,7 +1053,13 @@ 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)
@@ -1365,9 +1377,9 @@ 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
@@ -1375,10 +1387,13 @@ 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