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

[PATCH 09/32] object-file: Update the loose object map when writing loose objects

From
Eric W. Biederman <ebiederm@xmission.com>
Date
Sep 8, 2023, 23:10 UTC
Message-ID
<20230908231049.2035003-9-ebiederm@xmission.com>
In-Reply-To
<87sf7ol0z3.fsf@email.froward.int.ebiederm.org>

To implement SHA1 compatibility on SHA256 repositories the loose object map needs to be updated whenver a loose object is written. Updating the loose object map this way allows git to support the old hash algorithm in constant time.

The functions write_loose_object, and stream_loose_object are the only two functions that write to the loose object store.

Update stream_loose_object to compute the compatibiilty hash, update the loose object, and then call repo_add_loose_object_map to update the loose object map.

Update write_object_file_flags to convert the object into it's compatibility encoding, hash the compatibility encoding, write the object, and then update the loose object map.

Update force_object_loose to lookup the hash of the compatibility encoding, write the loose object, and then update the loose object map.

Update write_object_file_litterally to refuse to write any objects when a compatibility encoding is enabled. The problem is that write_object_file_literally is frequently used to write ill-formed objects. Especially when the type of those objects is changed there is by definition no possibile way to convert them, as no converstion has been defined.

Since a compatibilty encoding can not be found and a compatibility mapping can not be written the cleanest behavior is to simply disallow write_object_file_literraly from writing files.

Except that the loose objects are updated before the loose object map I have not done any analysis to see how robust this scheme is in the event of failure.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 object-file.c | 94 +++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 76 insertions(+), 18 deletions(-)
diff --git a/object-file.c b/object-file.c
index 7f24f19b8a68..6a14b8875343 100644
--- a/object-file.c
+++ b/object-file.c
@@ -44,6 +44,7 @@
 #include "setup.h"
 #include "submodule.h"
 #include "fsck.h"
+#include "loose.h"
 
 /* The maximum size for an object header. */
 #define MAX_HEADER_LEN 32
@@ -2035,9 +2036,12 @@ static int start_loose_object_common(struct strbuf *tmp_file,
 				     const char *filename, unsigned flags,
 				     git_zstream *stream,
 				     unsigned char *buf, size_t buflen,
-				     git_hash_ctx *c,
+				     git_hash_ctx *c, git_hash_ctx *compat_c,
 				     char *hdr, int hdrlen)
 {
+	struct repository *repo = the_repository;
+	const struct git_hash_algo *algo = repo->hash_algo;
+	const struct git_hash_algo *compat = repo->compat_hash_algo;
 	int fd;
 
 	fd = create_tmpfile(tmp_file, filename);
@@ -2057,14 +2061,18 @@ static int start_loose_object_common(struct strbuf *tmp_file,
 	git_deflate_init(stream, zlib_compression_level);
 	stream->next_out = buf;
 	stream->avail_out = buflen;
-	the_hash_algo->init_fn(c);
+	algo->init_fn(c);
+	if (compat && compat_c)
+		compat->init_fn(compat_c);
 
 	/*  Start to feed header to zlib stream */
 	stream->next_in = (unsigned char *)hdr;
 	stream->avail_in = hdrlen;
 	while (git_deflate(stream, 0) == Z_OK)
 		; /* nothing */
-	the_hash_algo->update_fn(c, hdr, hdrlen);
+	algo->update_fn(c, hdr, hdrlen);
+	if (compat && compat_c)
+		compat->update_fn(compat_c, hdr, hdrlen);
 
 	return fd;
 }
@@ -2073,16 +2081,21 @@ static int start_loose_object_common(struct strbuf *tmp_file,
  * Common steps for the inner git_deflate() loop for writing loose
  * objects. Returns what git_deflate() returns.
  */
-static int write_loose_object_common(git_hash_ctx *c,
+static int write_loose_object_common(git_hash_ctx *c, git_hash_ctx *compat_c,
 				     git_zstream *stream, const int flush,
 				     unsigned char *in0, const int fd,
 				     unsigned char *compressed,
 				     const size_t compressed_len)
 {
+	struct repository *repo = the_repository;
+	const struct git_hash_algo *algo = repo->hash_algo;
+	const struct git_hash_algo *compat = repo->compat_hash_algo;
 	int ret;
 
 	ret = git_deflate(stream, flush ? Z_FINISH : 0);
-	the_hash_algo->update_fn(c, in0, stream->next_in - in0);
+	algo->update_fn(c, in0, stream->next_in - in0);
+	if (compat && compat_c)
+		compat->update_fn(compat_c, in0, stream->next_in - in0);
 	if (write_in_full(fd, compressed, stream->next_out - compressed) < 0)
 		die_errno(_("unable to write loose object file"));
 	stream->next_out = compressed;
@@ -2097,15 +2110,21 @@ static int write_loose_object_common(git_hash_ctx *c,
  * - End the compression of zlib stream.
  * - Get the calculated oid to "oid".
  */
-static int end_loose_object_common(git_hash_ctx *c, git_zstream *stream,
-				   struct object_id *oid)
+static int end_loose_object_common(git_hash_ctx *c, git_hash_ctx *compat_c,
+				   git_zstream *stream, struct object_id *oid,
+				   struct object_id *compat_oid)
 {
+	struct repository *repo = the_repository;
+	const struct git_hash_algo *algo = repo->hash_algo;
+	const struct git_hash_algo *compat = repo->compat_hash_algo;
 	int ret;
 
 	ret = git_deflate_end_gently(stream);
 	if (ret != Z_OK)
 		return ret;
-	the_hash_algo->final_oid_fn(oid, c);
+	algo->final_oid_fn(oid, c);
+	if (compat && compat_c)
+		compat->final_oid_fn(compat_oid, compat_c);
 
 	return Z_OK;
 }
@@ -2129,7 +2148,7 @@ static int write_loose_object(const struct object_id *oid, char *hdr,
 
 	fd = start_loose_object_common(&tmp_file, filename.buf, flags,
 				       &stream, compressed, sizeof(compressed),
-				       &c, hdr, hdrlen);
+				       &c, NULL, hdr, hdrlen);
 	if (fd < 0)
 		return -1;
 
@@ -2139,14 +2158,14 @@ static int write_loose_object(const struct object_id *oid, char *hdr,
 	do {
 		unsigned char *in0 = stream.next_in;
 
-		ret = write_loose_object_common(&c, &stream, 1, in0, fd,
+		ret = write_loose_object_common(&c, NULL, &stream, 1, in0, fd,
 						compressed, sizeof(compressed));
 	} while (ret == Z_OK);
 
 	if (ret != Z_STREAM_END)
 		die(_("unable to deflate new object %s (%d)"), oid_to_hex(oid),
 		    ret);
-	ret = end_loose_object_common(&c, &stream, &parano_oid);
+	ret = end_loose_object_common(&c, NULL, &stream, &parano_oid, NULL);
 	if (ret != Z_OK)
 		die(_("deflateEnd on object %s failed (%d)"), oid_to_hex(oid),
 		    ret);
@@ -2191,10 +2210,12 @@ static int freshen_packed_object(const struct object_id *oid)
 int stream_loose_object(struct input_stream *in_stream, size_t len,
 			struct object_id *oid)
 {
+	const struct git_hash_algo *compat = the_repository->compat_hash_algo;
+	struct object_id compat_oid;
 	int fd, ret, err = 0, flush = 0;
 	unsigned char compressed[4096];
 	git_zstream stream;
-	git_hash_ctx c;
+	git_hash_ctx c, compat_c;
 	struct strbuf tmp_file = STRBUF_INIT;
 	struct strbuf filename = STRBUF_INIT;
 	int dirlen;
@@ -2218,7 +2239,7 @@ int stream_loose_object(struct input_stream *in_stream, size_t len,
 	 */
 	fd = start_loose_object_common(&tmp_file, filename.buf, 0,
 				       &stream, compressed, sizeof(compressed),
-				       &c, hdr, hdrlen);
+				       &c, &compat_c, hdr, hdrlen);
 	if (fd < 0) {
 		err = -1;
 		goto cleanup;
@@ -2236,7 +2257,7 @@ int stream_loose_object(struct input_stream *in_stream, size_t len,
 			if (in_stream->is_finished)
 				flush = 1;
 		}
-		ret = write_loose_object_common(&c, &stream, flush, in0, fd,
+		ret = write_loose_object_common(&c, &compat_c, &stream, flush, in0, fd,
 						compressed, sizeof(compressed));
 		/*
 		 * Unlike write_loose_object(), we do not have the entire
@@ -2259,7 +2280,7 @@ int stream_loose_object(struct input_stream *in_stream, size_t len,
 	 */
 	if (ret != Z_STREAM_END)
 		die(_("unable to stream deflate new object (%d)"), ret);
-	ret = end_loose_object_common(&c, &stream, oid);
+	ret = end_loose_object_common(&c, &compat_c, &stream, oid, &compat_oid);
 	if (ret != Z_OK)
 		die(_("deflateEnd on stream object failed (%d)"), ret);
 	close_loose_object(fd, tmp_file.buf);
@@ -2286,6 +2307,8 @@ int stream_loose_object(struct input_stream *in_stream, size_t len,
 	}
 
 	err = finalize_object_file(tmp_file.buf, filename.buf);
+	if (!err && compat)
+		err = repo_add_loose_object_map(the_repository, oid, &compat_oid);
 cleanup:
 	strbuf_release(&tmp_file);
 	strbuf_release(&filename);
@@ -2296,17 +2319,38 @@ int write_object_file_flags(const void *buf, unsigned long len,
 			    enum object_type type, struct object_id *oid,
 			    unsigned flags)
 {
+	struct repository *repo = the_repository;
+	const struct git_hash_algo *algo = repo->hash_algo;
+	const struct git_hash_algo *compat = repo->compat_hash_algo;
+	struct object_id compat_oid;
 	char hdr[MAX_HEADER_LEN];
 	int hdrlen = sizeof(hdr);
 
+	/* Generate compat_oid */
+	if (compat) {
+		if (type == OBJ_BLOB)
+			hash_object_file(compat, buf, len, type, &compat_oid);
+		else {
+			struct strbuf converted = STRBUF_INIT;
+			convert_object_file(&converted, algo, compat,
+					    buf, len, type, 0);
+			hash_object_file(compat, converted.buf, converted.len,
+					 type, &compat_oid);
+			strbuf_release(&converted);
+		}
+	}
+
 	/* Normally if we have it in the pack then we do not bother writing
 	 * it out into .git/objects/??/?{38} file.
 	 */
-	write_object_file_prepare(the_hash_algo, buf, len, type, oid, hdr,
-				  &hdrlen);
+	write_object_file_prepare(algo, buf, len, type, oid, hdr, &hdrlen);
 	if (freshen_packed_object(oid) || freshen_loose_object(oid))
 		return 0;
-	return write_loose_object(oid, hdr, hdrlen, buf, len, 0, flags);
+	if (write_loose_object(oid, hdr, hdrlen, buf, len, 0, flags))
+		return -1;
+	if (compat)
+		return repo_add_loose_object_map(repo, oid, &compat_oid);
+	return 0;
 }
 
 int write_object_file_literally(const void *buf, unsigned long len,
@@ -2324,6 +2368,10 @@ int write_object_file_literally(const void *buf, unsigned long len,
 
 	if (!(flags & HASH_WRITE_OBJECT))
 		goto cleanup;
+	else if (the_repository->compat_hash_algo) {
+		status = -1;
+		goto cleanup;
+	}
 	if (freshen_packed_object(oid) || freshen_loose_object(oid))
 		goto cleanup;
 	status = write_loose_object(oid, header, hdrlen, buf, len, 0, 0);
@@ -2335,9 +2383,12 @@ int write_object_file_literally(const void *buf, unsigned long len,
 
 int force_object_loose(const struct object_id *oid, time_t mtime)
 {
+	struct repository *repo = the_repository;
+	const struct git_hash_algo *compat = repo->compat_hash_algo;
 	void *buf;
 	unsigned long len;
 	struct object_info oi = OBJECT_INFO_INIT;
+	struct object_id compat_oid;
 	enum object_type type;
 	char hdr[MAX_HEADER_LEN];
 	int hdrlen;
@@ -2350,8 +2401,15 @@ int force_object_loose(const struct object_id *oid, time_t mtime)
 	oi.contentp = &buf;
 	if (oid_object_info_extended(the_repository, oid, &oi, 0))
 		return error(_("cannot read object for %s"), oid_to_hex(oid));
+	if (compat) {
+		if (repo_oid_to_algop(repo, oid, compat, &compat_oid))
+			return error(_("cannot map object %s to %s"),
+				     oid_to_hex(oid), compat->name);
+	}
 	hdrlen = format_object_header(hdr, sizeof(hdr), type, len);
 	ret = write_loose_object(oid, hdr, hdrlen, buf, len, mtime, 0);
+	if (!ret && compat)
+		ret = repo_add_loose_object_map(the_repository, oid, &compat_oid);
 	free(buf);
 
 	return ret;
-- 
2.41.0
Previous: Eric W. BiedermanNext: Eric W. Biederman
Message 47 of 59 in “SHA256 and SHA1 interoperability”
  1. Eric W. BiedermanSep 8, 2023
  2. 02/32 doc hash-function-transition: Replace compatObjectFormat with compatMapEric W. Biederman, Sep 8, 2023
  3. brian m. carlsonSep 10, 2023
  4. Eric W. BiedermanSep 10, 2023
  5. Junio C HamanoSep 11, 2023
  6. 02/32 doc hash-function-transition: Replace compatObjectFormat with mapObjectFormatEric W. Biederman, Sep 11, 2023
  7. 02/32 doc hash-function-transition: Augment compatObjectFormat with readCompatMapEric W. Biederman, Sep 11, 2023
  8. Oswald BuddenhagenSep 12, 2023
  9. Eric W. BiedermanSep 12, 2023
  10. Oswald BuddenhagenSep 13, 2023
  11. 04/32 object-name: Initial support for ^{sha1} and ^{sha256}Eric W. Biederman, Sep 8, 2023
  12. 06/32 repository: Implement core.compatMapEric W. Biederman, Sep 8, 2023
  13. 07/32 loose: add a mapping between SHA-1 and SHA-256 for loose objectsEric W. Biederman, Sep 8, 2023
  14. 19/32 object-file-convert: convert tag commits when writingEric W. Biederman, Sep 8, 2023
  15. 20/32 builtin/cat-file: Let the oid determine the output algorithmEric W. Biederman, Sep 8, 2023
  16. 22/32 object-file: Handle compat objects in check_object_signatureEric W. Biederman, Sep 8, 2023
  17. 26/32 object-file-convert: Implement convert_object_file_{begin,step,end}Eric W. Biederman, Sep 8, 2023
  18. Junio C HamanoSep 11, 2023
  19. 27/32 builtin/fast-import: compute compatibility hashs for imported objectsEric W. Biederman, Sep 8, 2023
  20. 29/32 builtin/index-pack: Compute the compatibility hashEric W. Biederman, Sep 8, 2023
  21. 31/32 unpack-objects: Update to compute and write the compatibility hashesEric W. Biederman, Sep 8, 2023
  22. 16/32 object: Factor out parse_mode out of fast-import and tree-walk into in object.hEric W. Biederman, Sep 8, 2023
  23. 10/32 bulk-checkin: Only accept blobsEric W. Biederman, Sep 8, 2023
  24. 23/32 builtin/ls-tree: Let the oid determine the output algorithmEric W. Biederman, Sep 8, 2023
  25. 12/32 bulk-checkin: hash object with compatibility algorithmEric W. Biederman, Sep 8, 2023
  26. Junio C HamanoSep 11, 2023
  27. 14/32 commit: write commits for both hashesEric W. Biederman, Sep 8, 2023
  28. Junio C HamanoSep 11, 2023
  29. 03/32 object-file-convert: Stubs for converting from one object format to anotherEric W. Biederman, Sep 8, 2023
  30. 08/32 loose: Compatibilty short name supportEric W. Biederman, Sep 8, 2023
  31. 01/32 doc hash-file-transition: A map file for mapping between sha1 and sha256Eric W. Biederman, Sep 8, 2023
  32. brian m. carlsonSep 10, 2023
  33. Eric W. BiedermanSep 10, 2023
  34. brian m. carlsonSep 12, 2023
  35. Eric W. BiedermanSep 12, 2023
  36. 15/32 cache: add a function to read an OID of a specific algorithmEric W. Biederman, Sep 8, 2023
  37. 32/32 object-file-convert: Implement repo_submodule_oid_to_algopEric W. Biederman, Sep 8, 2023
  38. 30/32 builtin/index-pack: Make the stack in compute_compat_oid explicitEric W. Biederman, Sep 8, 2023
  39. 28/32 builtin/index-pack: Add a simple oid indexEric W. Biederman, Sep 8, 2023
  40. 25/32 pack-compat-map: Add support for .compat files of a packfileEric W. Biederman, Sep 8, 2023
  41. Junio C HamanoSep 11, 2023
  42. Taylor BlauOct 5, 2023
  43. 21/32 tree-walk: init_tree_desc take an oid to get the hash algorithmEric W. Biederman, Sep 8, 2023
  44. 24/32 builtin/pack-objects: Communicate the compatibility hash through struct pack_idx_entryEric W. Biederman, Sep 8, 2023
  45. 18/32 object-file-convert: convert commit objects when writingEric W. Biederman, Sep 8, 2023
  46. 17/32 object-file-convert: add a function to convert trees between algorithmsEric W. Biederman, Sep 8, 2023
  47. 09/32 object-file: Update the loose object map when writing loose objectsEric W. Biederman, Sep 8, 2023
  48. 11/32 pack: Communicate the compat_oid through struct pack_idx_entryEric W. Biederman, Sep 8, 2023
  49. 05/32 repository: add a compatibility hash algorithmEric W. Biederman, Sep 8, 2023
  50. 13/32 object-file: Add a compat_oid_in parameter to write_object_file_flagsEric W. Biederman, Sep 8, 2023
  51. Eric W. BiedermanSep 9, 2023
  52. brian m. carlsonSep 10, 2023
  53. Eric W. BiedermanSep 10, 2023
  54. Junio C HamanoSep 11, 2023
  55. Eric W. BiedermanSep 11, 2023
  56. brian m. carlsonSep 11, 2023
  57. Eric W. BiedermanSep 12, 2023
  58. Junio C HamanoSep 12, 2023
  59. Eric W. BiedermanSep 14, 2023

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.