git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH v2 04/13] hash: add a function to finalize object IDs

From
brian m. carlson <sandals@crustytoothpaste.net>
Date
Apr 26, 2021, 01:02 UTC
Message-ID
<20210426010301.1093562-5-sandals@crustytoothpaste.net>
In-Reply-To
<20210426010301.1093562-1-sandals@crustytoothpaste.net>

To avoid the penalty of having to branch in hash comparison functions, we'll want to always compare the full hash member in a struct object_id, which will require that SHA-1 object IDs be zero-padded. To do so, add a function which finalizes a hash context and writes it into an object ID that performs this padding.

Move the definition of struct object_id and the constant definitions higher up so we they are available for us to use.

Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
---
 hash.h        | 50 +++++++++++++++++++++++++++-----------------------
 object-file.c | 25 +++++++++++++++++++++++++
 2 files changed, 52 insertions(+), 23 deletions(-)
diff --git a/hash.h b/hash.h
index dafdcb3335..c8f03d8aee 100644
--- a/hash.h
+++ b/hash.h
@@ -95,6 +95,29 @@ static inline void git_SHA256_Clone(git_SHA256_CTX *dst, const git_SHA256_CTX *s
 /* Number of algorithms supported (including unknown). */
 #define GIT_HASH_NALGOS (GIT_HASH_SHA256 + 1)
 
+/* 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_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];
+	int algo;
+};
+
 /* A suitably aligned type for stack allocations of hash contexts. */
 union git_hash_ctx {
 	git_SHA_CTX sha1;
@@ -106,6 +129,7 @@ typedef void (*git_hash_init_fn)(git_hash_ctx *ctx);
 typedef void (*git_hash_clone_fn)(git_hash_ctx *dst, const git_hash_ctx *src);
 typedef void (*git_hash_update_fn)(git_hash_ctx *ctx, const void *in, size_t len);
 typedef void (*git_hash_final_fn)(unsigned char *hash, git_hash_ctx *ctx);
+typedef void (*git_hash_final_oid_fn)(struct object_id *oid, git_hash_ctx *ctx);
 
 struct git_hash_algo {
 	/*
@@ -138,6 +162,9 @@ struct git_hash_algo {
 	/* The hash finalization function. */
 	git_hash_final_fn final_fn;
 
+	/* The hash finalization function for object IDs. */
+	git_hash_final_oid_fn final_oid_fn;
+
 	/* The OID of the empty tree. */
 	const struct object_id *empty_tree;
 
@@ -161,29 +188,6 @@ static inline int hash_algo_by_ptr(const struct git_hash_algo *p)
 	return p - hash_algos;
 }
 
-/* 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_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];
-	int algo;
-};
-
 #define the_hash_algo the_repository->hash_algo
 
 extern const struct object_id null_oid;
diff --git a/object-file.c b/object-file.c
index 624af408cd..ef1eb984c8 100644
--- a/object-file.c
+++ b/object-file.c
@@ -89,6 +89,12 @@ static void git_hash_sha1_final(unsigned char *hash, git_hash_ctx *ctx)
 	git_SHA1_Final(hash, &ctx->sha1);
 }
 
+static void git_hash_sha1_final_oid(struct object_id *oid, git_hash_ctx *ctx)
+{
+	git_SHA1_Final(oid->hash, &ctx->sha1);
+	memset(oid->hash + GIT_SHA1_RAWSZ, 0, GIT_MAX_RAWSZ - GIT_SHA1_RAWSZ);
+}
+
 
 static void git_hash_sha256_init(git_hash_ctx *ctx)
 {
@@ -110,6 +116,16 @@ static void git_hash_sha256_final(unsigned char *hash, git_hash_ctx *ctx)
 	git_SHA256_Final(hash, &ctx->sha256);
 }
 
+static void git_hash_sha256_final_oid(struct object_id *oid, git_hash_ctx *ctx)
+{
+	git_SHA256_Final(oid->hash, &ctx->sha256);
+	/*
+	 * This currently does nothing, so the compiler should optimize it out,
+	 * but keep it in case we extend the hash size again.
+	 */
+	memset(oid->hash + GIT_SHA256_RAWSZ, 0, GIT_MAX_RAWSZ - GIT_SHA256_RAWSZ);
+}
+
 static void git_hash_unknown_init(git_hash_ctx *ctx)
 {
 	BUG("trying to init unknown hash");
@@ -130,6 +146,12 @@ static void git_hash_unknown_final(unsigned char *hash, git_hash_ctx *ctx)
 	BUG("trying to finalize unknown hash");
 }
 
+static void git_hash_unknown_final_oid(struct object_id *oid, git_hash_ctx *ctx)
+{
+	BUG("trying to finalize unknown hash");
+}
+
+
 const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = {
 	{
 		NULL,
@@ -141,6 +163,7 @@ const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = {
 		git_hash_unknown_clone,
 		git_hash_unknown_update,
 		git_hash_unknown_final,
+		git_hash_unknown_final_oid,
 		NULL,
 		NULL,
 	},
@@ -155,6 +178,7 @@ const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = {
 		git_hash_sha1_clone,
 		git_hash_sha1_update,
 		git_hash_sha1_final,
+		git_hash_sha1_final_oid,
 		&empty_tree_oid,
 		&empty_blob_oid,
 	},
@@ -169,6 +193,7 @@ const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = {
 		git_hash_sha256_clone,
 		git_hash_sha256_update,
 		git_hash_sha256_final,
+		git_hash_sha256_final_oid,
 		&empty_tree_oid_sha256,
 		&empty_blob_oid_sha256,
 	}
Previous: brian m. carlsonNext: brian m. carlson
Message 12 of 16 in “SHA-256 / SHA-1 interop, part 1”
  1. 00/13 SHA-256 / SHA-1 interop, part 1brian m. carlson, Apr 26, 2021
  2. 01/13 hash: add an algo member to struct object_idbrian m. carlson, Apr 26, 2021
  3. Matheus Tavares BernardinoMay 7, 2021
  4. brian m. carlsonMay 7, 2021
  5. 03/13 http-push: set algorithm when reading object IDbrian m. carlson, Apr 26, 2021
  6. 06/13 builtin/pack-redundant: avoid casting buffers to struct object_idbrian m. carlson, Apr 26, 2021
  7. 02/13 Always use oidread to read into struct object_idbrian m. carlson, Apr 26, 2021
  8. 07/13 hash: set, copy, and use algo field in struct object_idbrian m. carlson, Apr 26, 2021
  9. 10/13 commit-graph: don't store file hashes as struct object_idbrian m. carlson, Apr 26, 2021
  10. 11/13 builtin/pack-objects: avoid using struct object_id for pack hashbrian m. carlson, Apr 26, 2021
  11. 13/13 hex: print objects using the hash algorithm memberbrian m. carlson, Apr 26, 2021
  12. 04/13 hash: add a function to finalize object IDsbrian m. carlson, Apr 26, 2021
  13. 05/13 Use the final_oid_fn to finalize hashing of object IDsbrian m. carlson, Apr 26, 2021
  14. 08/13 hash: provide per-algorithm null OIDsbrian m. carlson, Apr 26, 2021
  15. 09/13 builtin/show-index: set the algorithm for object IDsbrian m. carlson, Apr 26, 2021
  16. 12/13 hex: default to the_hash_algo on zero algorithm valuebrian m. carlson, Apr 26, 2021

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.