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

[PATCH v4 6/8] hash.h: scaffolding for _unsafe hashing variants

From
Taylor Blau <me@ttaylorr.com>
Date
Sep 24, 2024, 17:32 UTC
Message-ID
<d300e9c68879faf837c65455e39b4aa07c1e1b03.1727199118.git.me@ttaylorr.com>
In-Reply-To
<cover.1727199118.git.me@ttaylorr.com>

Git's default SHA-1 implementation is collision-detecting, which hardens us against known SHA-1 attacks against Git objects. This makes Git object writes safer at the expense of some speed when hashing through the collision-detecting implementation, which is slower than non-collision detecting alternatives.

Prepare for loading a separate "unsafe" SHA-1 implementation that can be used for non-cryptographic purposes, like computing the checksum of files that use the hashwrite() API.

This commit does not actually introduce any new compile-time knobs to control which implementation is used as the unsafe SHA-1 variant, but does add scaffolding so that the "git_hash_algo" structure has five new function pointers which are "unsafe" variants of the five existing hashing-related function pointers:

  - git_hash_init_fn unsafe_init_fn
  - git_hash_clone_fn unsafe_clone_fn
  - git_hash_update_fn unsafe_update_fn
  - git_hash_final_fn unsafe_final_fn
  - git_hash_final_oid_fn unsafe_final_oid_fn

The following commit will introduce compile-time knobs to specify which SHA-1 implementation is used for non-cryptographic uses.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 hash.h        | 42 ++++++++++++++++++++++++++++++++++++++++++
 object-file.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 84 insertions(+)
diff --git a/hash.h b/hash.h
index 72ffbc862e5..96458b129f9 100644
--- a/hash.h
+++ b/hash.h
@@ -44,14 +44,32 @@
 #define platform_SHA1_Final    	SHA1_Final
 #endif
 
+#ifndef platform_SHA_CTX_unsafe
+#  define platform_SHA_CTX_unsafe      platform_SHA_CTX
+#  define platform_SHA1_Init_unsafe    platform_SHA1_Init
+#  define platform_SHA1_Update_unsafe  platform_SHA1_Update
+#  define platform_SHA1_Final_unsafe   platform_SHA1_Final
+#  ifdef platform_SHA1_Clone
+#    define platform_SHA1_Clone_unsafe platform_SHA1_Clone
+#  endif
+#endif
+
 #define git_SHA_CTX		platform_SHA_CTX
 #define git_SHA1_Init		platform_SHA1_Init
 #define git_SHA1_Update		platform_SHA1_Update
 #define git_SHA1_Final		platform_SHA1_Final
 
+#define git_SHA_CTX_unsafe	platform_SHA_CTX_unsafe
+#define git_SHA1_Init_unsafe	platform_SHA1_Init_unsafe
+#define git_SHA1_Update_unsafe	platform_SHA1_Update_unsafe
+#define git_SHA1_Final_unsafe	platform_SHA1_Final_unsafe
+
 #ifdef platform_SHA1_Clone
 #define git_SHA1_Clone	platform_SHA1_Clone
 #endif
+#ifdef platform_SHA1_Clone_unsafe
+#  define git_SHA1_Clone_unsafe platform_SHA1_Clone_unsafe
+#endif
 
 #ifndef platform_SHA256_CTX
 #define platform_SHA256_CTX	SHA256_CTX
@@ -81,6 +99,13 @@ static inline void git_SHA1_Clone(git_SHA_CTX *dst, const git_SHA_CTX *src)
 	memcpy(dst, src, sizeof(*dst));
 }
 #endif
+#ifndef SHA1_NEEDS_CLONE_HELPER_UNSAFE
+static inline void git_SHA1_Clone_unsafe(git_SHA_CTX_unsafe *dst,
+				       const git_SHA_CTX_unsafe *src)
+{
+	memcpy(dst, src, sizeof(*dst));
+}
+#endif
 
 #ifndef SHA256_NEEDS_CLONE_HELPER
 static inline void git_SHA256_Clone(git_SHA256_CTX *dst, const git_SHA256_CTX *src)
@@ -178,6 +203,8 @@ enum get_oid_result {
 /* A suitably aligned type for stack allocations of hash contexts. */
 union git_hash_ctx {
 	git_SHA_CTX sha1;
+	git_SHA_CTX_unsafe sha1_unsafe;
+
 	git_SHA256_CTX sha256;
 };
 typedef union git_hash_ctx git_hash_ctx;
@@ -222,6 +249,21 @@ struct git_hash_algo {
 	/* The hash finalization function for object IDs. */
 	git_hash_final_oid_fn final_oid_fn;
 
+	/* The non-cryptographic hash initialization function. */
+	git_hash_init_fn unsafe_init_fn;
+
+	/* The non-cryptographic hash context cloning function. */
+	git_hash_clone_fn unsafe_clone_fn;
+
+	/* The non-cryptographic hash update function. */
+	git_hash_update_fn unsafe_update_fn;
+
+	/* The non-cryptographic hash finalization function. */
+	git_hash_final_fn unsafe_final_fn;
+
+	/* The non-cryptographic hash finalization function. */
+	git_hash_final_oid_fn unsafe_final_oid_fn;
+
 	/* The OID of the empty tree. */
 	const struct object_id *empty_tree;
 
diff --git a/object-file.c b/object-file.c
index b9a3a1f62db..196c9e2df8b 100644
--- a/object-file.c
+++ b/object-file.c
@@ -115,6 +115,33 @@ static void git_hash_sha1_final_oid(struct object_id *oid, git_hash_ctx *ctx)
 	oid->algo = GIT_HASH_SHA1;
 }
 
+static void git_hash_sha1_init_unsafe(git_hash_ctx *ctx)
+{
+	git_SHA1_Init_unsafe(&ctx->sha1_unsafe);
+}
+
+static void git_hash_sha1_clone_unsafe(git_hash_ctx *dst, const git_hash_ctx *src)
+{
+	git_SHA1_Clone_unsafe(&dst->sha1_unsafe, &src->sha1_unsafe);
+}
+
+static void git_hash_sha1_update_unsafe(git_hash_ctx *ctx, const void *data,
+				      size_t len)
+{
+	git_SHA1_Update_unsafe(&ctx->sha1_unsafe, data, len);
+}
+
+static void git_hash_sha1_final_unsafe(unsigned char *hash, git_hash_ctx *ctx)
+{
+	git_SHA1_Final_unsafe(hash, &ctx->sha1_unsafe);
+}
+
+static void git_hash_sha1_final_oid_unsafe(struct object_id *oid, git_hash_ctx *ctx)
+{
+	git_SHA1_Final_unsafe(oid->hash, &ctx->sha1_unsafe);
+	memset(oid->hash + GIT_SHA1_RAWSZ, 0, GIT_MAX_RAWSZ - GIT_SHA1_RAWSZ);
+	oid->algo = GIT_HASH_SHA1;
+}
 
 static void git_hash_sha256_init(git_hash_ctx *ctx)
 {
@@ -189,6 +216,11 @@ const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = {
 		.update_fn = git_hash_unknown_update,
 		.final_fn = git_hash_unknown_final,
 		.final_oid_fn = git_hash_unknown_final_oid,
+		.unsafe_init_fn = git_hash_unknown_init,
+		.unsafe_clone_fn = git_hash_unknown_clone,
+		.unsafe_update_fn = git_hash_unknown_update,
+		.unsafe_final_fn = git_hash_unknown_final,
+		.unsafe_final_oid_fn = git_hash_unknown_final_oid,
 		.empty_tree = NULL,
 		.empty_blob = NULL,
 		.null_oid = NULL,
@@ -204,6 +236,11 @@ const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = {
 		.update_fn = git_hash_sha1_update,
 		.final_fn = git_hash_sha1_final,
 		.final_oid_fn = git_hash_sha1_final_oid,
+		.unsafe_init_fn = git_hash_sha1_init_unsafe,
+		.unsafe_clone_fn = git_hash_sha1_clone_unsafe,
+		.unsafe_update_fn = git_hash_sha1_update_unsafe,
+		.unsafe_final_fn = git_hash_sha1_final_unsafe,
+		.unsafe_final_oid_fn = git_hash_sha1_final_oid_unsafe,
 		.empty_tree = &empty_tree_oid,
 		.empty_blob = &empty_blob_oid,
 		.null_oid = &null_oid_sha1,
@@ -219,6 +256,11 @@ const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = {
 		.update_fn = git_hash_sha256_update,
 		.final_fn = git_hash_sha256_final,
 		.final_oid_fn = git_hash_sha256_final_oid,
+		.unsafe_init_fn = git_hash_sha256_init,
+		.unsafe_clone_fn = git_hash_sha256_clone,
+		.unsafe_update_fn = git_hash_sha256_update,
+		.unsafe_final_fn = git_hash_sha256_final,
+		.unsafe_final_oid_fn = git_hash_sha256_final_oid,
 		.empty_tree = &empty_tree_oid_sha256,
 		.empty_blob = &empty_blob_oid_sha256,
 		.null_oid = &null_oid_sha256,
-- 
2.46.2.636.g4b83dd05e9f
Previous: Taylor BlauNext: Taylor Blau
Message 80 of 99 in “hash.h: support choosing a separate SHA-1 for non-cryptographic uses”
  1. 0/4 hash.h: support choosing a separate SHA-1 for non-cryptographic usesTaylor Blau, Sep 1, 2024
  2. 1/4 sha1: do not redefine `platform_SHA_CTX` and friendsTaylor Blau, Sep 1, 2024
  3. Patrick SteinhardtSep 2, 2024
  4. Taylor BlauSep 3, 2024
  5. 2/4 hash.h: scaffolding for _fast hashing variantsTaylor Blau, Sep 1, 2024
  6. Patrick SteinhardtSep 2, 2024
  7. Junio C HamanoSep 3, 2024
  8. Taylor BlauSep 3, 2024
  9. Junio C HamanoSep 3, 2024
  10. Taylor BlauSep 3, 2024
  11. Patrick SteinhardtSep 4, 2024
  12. Junio C HamanoSep 4, 2024
  13. Taylor BlauSep 3, 2024
  14. 3/4 Makefile: allow specifying a SHA-1 for non-cryptographic usesTaylor Blau, Sep 1, 2024
  15. Patrick SteinhardtSep 2, 2024
  16. Taylor BlauSep 3, 2024
  17. 4/4 csum-file.c: use fast SHA-1 implementation when availableTaylor Blau, Sep 1, 2024
  18. Patrick SteinhardtSep 2, 2024
  19. brian m. carlsonSep 3, 2024
  20. Taylor BlauSep 3, 2024
  21. Junio C HamanoSep 2, 2024
  22. Taylor BlauSep 3, 2024
  23. Junio C HamanoSep 3, 2024
  24. brian m. carlsonSep 2, 2024
  25. Taylor BlauSep 3, 2024
  26. Junio C HamanoSep 3, 2024
  27. brian m. carlsonSep 4, 2024
  28. Jeff KingSep 5, 2024
  29. Junio C HamanoSep 5, 2024
  30. Taylor BlauSep 5, 2024
  31. Junio C HamanoSep 5, 2024
  32. Taylor BlauSep 5, 2024
  33. Taylor BlauSep 5, 2024
  34. Taylor BlauSep 5, 2024
  35. Jeff KingSep 5, 2024
  36. Junio C HamanoSep 5, 2024
  37. 0/4 hash.h: support choosing a separate SHA-1 for non-cryptographic usesTaylor Blau, Sep 5, 2024
  38. 1/4 sha1: do not redefine `platform_SHA_CTX` and friendsTaylor Blau, Sep 5, 2024
  39. 2/4 hash.h: scaffolding for _fast hashing variantsTaylor Blau, Sep 5, 2024
  40. 3/4 Makefile: allow specifying a SHA-1 for non-cryptographic usesTaylor Blau, Sep 5, 2024
  41. 4/4 csum-file.c: use fast SHA-1 implementation when availableTaylor Blau, Sep 5, 2024
  42. 0/9 hash.h: support choosing a separate SHA-1 for non-cryptographic usesTaylor Blau, Sep 6, 2024
  43. 1/9 finalize_object_file(): check for name collision before renamingTaylor Blau, Sep 6, 2024
  44. 2/9 finalize_object_file(): refactor unlink_or_warn() placementTaylor Blau, Sep 6, 2024
  45. 3/9 finalize_object_file(): implement collision checkTaylor Blau, Sep 6, 2024
  46. Junio C HamanoSep 6, 2024
  47. Chris TorekSep 6, 2024
  48. Jeff KingSep 10, 2024
  49. Junio C HamanoSep 10, 2024
  50. Patrick SteinhardtSep 16, 2024
  51. Taylor BlauSep 16, 2024
  52. Taylor BlauSep 16, 2024
  53. Junio C HamanoSep 17, 2024
  54. 4/9 pack-objects: use finalize_object_file() to rename pack/idx/etcTaylor Blau, Sep 6, 2024
  55. 5/9 i5500-git-daemon.sh: use compile-able version of Git without OpenSSLTaylor Blau, Sep 6, 2024
  56. Jeff KingSep 11, 2024
  57. Jeff KingSep 11, 2024
  58. Junio C HamanoSep 12, 2024
  59. Junio C HamanoSep 11, 2024
  60. Jeff KingSep 11, 2024
  61. 6/9 sha1: do not redefine `platform_SHA_CTX` and friendsTaylor Blau, Sep 6, 2024
  62. 7/9 hash.h: scaffolding for _fast hashing variantsTaylor Blau, Sep 6, 2024
  63. 8/9 Makefile: allow specifying a SHA-1 for non-cryptographic usesTaylor Blau, Sep 6, 2024
  64. 9/9 csum-file.c: use fast SHA-1 implementation when availableTaylor Blau, Sep 6, 2024
  65. Junio C HamanoSep 6, 2024
  66. 0/8 hash.h: support choosing a separate SHA-1 for non-cryptographic usesTaylor Blau, Sep 24, 2024
  67. 1/8 finalize_object_file(): check for name collision before renamingTaylor Blau, Sep 24, 2024
  68. Junio C HamanoSep 25, 2024
  69. 2/8 finalize_object_file(): refactor unlink_or_warn() placementTaylor Blau, Sep 24, 2024
  70. 3/8 finalize_object_file(): implement collision checkTaylor Blau, Sep 24, 2024
  71. Jeff KingSep 24, 2024
  72. Taylor BlauSep 24, 2024
  73. Jeff KingSep 24, 2024
  74. Taylor BlauSep 25, 2024
  75. Junio C HamanoSep 24, 2024
  76. Taylor BlauSep 24, 2024
  77. 4/8 pack-objects: use finalize_object_file() to rename pack/idx/etcTaylor Blau, Sep 24, 2024
  78. Junio C HamanoSep 24, 2024
  79. 5/8 sha1: do not redefine `platform_SHA_CTX` and friendsTaylor Blau, Sep 24, 2024
  80. 6/8 hash.h: scaffolding for _unsafe hashing variantsTaylor Blau, Sep 24, 2024
  81. 7/8 Makefile: allow specifying a SHA-1 for non-cryptographic usesTaylor Blau, Sep 24, 2024
  82. 8/8 csum-file.c: use unsafe SHA-1 implementation when availableTaylor Blau, Sep 24, 2024
  83. Jeff KingSep 24, 2024
  84. Elijah NewrenSep 25, 2024
  85. Junio C HamanoSep 25, 2024
  86. Taylor BlauSep 25, 2024
  87. Taylor BlauSep 25, 2024
  88. 0/8 hash.h: support choosing a separate SHA-1 for non-cryptographic usesTaylor Blau, Sep 26, 2024
  89. 1/8 finalize_object_file(): check for name collision before renamingTaylor Blau, Sep 26, 2024
  90. 2/8 finalize_object_file(): refactor unlink_or_warn() placementTaylor Blau, Sep 26, 2024
  91. 3/8 finalize_object_file(): implement collision checkTaylor Blau, Sep 26, 2024
  92. 4/8 pack-objects: use finalize_object_file() to rename pack/idx/etcTaylor Blau, Sep 26, 2024
  93. 5/8 sha1: do not redefine `platform_SHA_CTX` and friendsTaylor Blau, Sep 26, 2024
  94. 6/8 hash.h: scaffolding for _unsafe hashing variantsTaylor Blau, Sep 26, 2024
  95. 7/8 Makefile: allow specifying a SHA-1 for non-cryptographic usesTaylor Blau, Sep 26, 2024
  96. 8/8 csum-file.c: use unsafe SHA-1 implementation when availableTaylor Blau, Sep 26, 2024
  97. Elijah NewrenSep 26, 2024
  98. Junio C HamanoSep 27, 2024
  99. Jeff KingSep 27, 2024

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.