diff mbox series

[v2,2/4] hash.h: scaffolding for _fast hashing variants

Message ID 3b5f21e4a620b0afd706ec3a3fbb71918f96198f.1725549065.git.me@ttaylorr.com (mailing list archive)
State Superseded
Headers show
Series hash.h: support choosing a separate SHA-1 for non-cryptographic uses | expand

Commit Message

Taylor Blau Sept. 5, 2024, 3:12 p.m. UTC
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 "fast" 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 fast SHA-1 variant, but does
add scaffolding so that the "git_hash_algo" structure has five new
function pointers which are "fast" variants of the five existing
hashing-related function pointers:

  - git_hash_init_fn fast_init_fn
  - git_hash_clone_fn fast_clone_fn
  - git_hash_update_fn fast_update_fn
  - git_hash_final_fn fast_final_fn
  - git_hash_final_oid_fn fast_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 mbox series

Patch

diff --git a/hash.h b/hash.h
index 72ffbc862e5..5e5b8205b58 100644
--- a/hash.h
+++ b/hash.h
@@ -44,14 +44,32 @@ 
 #define platform_SHA1_Final    	SHA1_Final
 #endif
 
+#ifndef platform_SHA_CTX_fast
+#  define platform_SHA_CTX_fast     platform_SHA_CTX
+#  define platform_SHA1_Init_fast   platform_SHA1_Init
+#  define platform_SHA1_Update_fast platform_SHA1_Update
+#  define platform_SHA1_Final_fast  platform_SHA1_Final
+#  ifdef platform_SHA1_Clone
+#    define platform_SHA1_Clone_fast 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_fast	platform_SHA_CTX_fast
+#define git_SHA1_Init_fast	platform_SHA1_Init_fast
+#define git_SHA1_Update_fast	platform_SHA1_Update_fast
+#define git_SHA1_Final_fast	platform_SHA1_Final_fast
+
 #ifdef platform_SHA1_Clone
 #define git_SHA1_Clone	platform_SHA1_Clone
 #endif
+#ifdef platform_SHA1_Clone_fast
+#  define git_SHA1_Clone_fast platform_SHA1_Clone_fast
+#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_FAST
+static inline void git_SHA1_Clone_fast(git_SHA_CTX_fast *dst,
+				       const git_SHA_CTX_fast *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_fast sha1_fast;
+
 	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 fast / non-cryptographic hash initialization function. */
+	git_hash_init_fn fast_init_fn;
+
+	/* The fast / non-cryptographic hash context cloning function. */
+	git_hash_clone_fn fast_clone_fn;
+
+	/* The fast / non-cryptographic hash update function. */
+	git_hash_update_fn fast_update_fn;
+
+	/* The fast / non-cryptographic hash finalization function. */
+	git_hash_final_fn fast_final_fn;
+
+	/* The fast / non-cryptographic hash finalization function. */
+	git_hash_final_oid_fn fast_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 c5994202ba0..9691292ef5a 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_fast(git_hash_ctx *ctx)
+{
+	git_SHA1_Init_fast(&ctx->sha1_fast);
+}
+
+static void git_hash_sha1_clone_fast(git_hash_ctx *dst, const git_hash_ctx *src)
+{
+	git_SHA1_Clone_fast(&dst->sha1_fast, &src->sha1_fast);
+}
+
+static void git_hash_sha1_update_fast(git_hash_ctx *ctx, const void *data,
+				      size_t len)
+{
+	git_SHA1_Update_fast(&ctx->sha1_fast, data, len);
+}
+
+static void git_hash_sha1_final_fast(unsigned char *hash, git_hash_ctx *ctx)
+{
+	git_SHA1_Final_fast(hash, &ctx->sha1_fast);
+}
+
+static void git_hash_sha1_final_oid_fast(struct object_id *oid, git_hash_ctx *ctx)
+{
+	git_SHA1_Final_fast(oid->hash, &ctx->sha1_fast);
+	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,
+		.fast_init_fn = git_hash_unknown_init,
+		.fast_clone_fn = git_hash_unknown_clone,
+		.fast_update_fn = git_hash_unknown_update,
+		.fast_final_fn = git_hash_unknown_final,
+		.fast_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,
+		.fast_init_fn = git_hash_sha1_init_fast,
+		.fast_clone_fn = git_hash_sha1_clone_fast,
+		.fast_update_fn = git_hash_sha1_update_fast,
+		.fast_final_fn = git_hash_sha1_final_fast,
+		.fast_final_oid_fn = git_hash_sha1_final_oid_fast,
 		.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,
+		.fast_init_fn = git_hash_sha256_init,
+		.fast_clone_fn = git_hash_sha256_clone,
+		.fast_update_fn = git_hash_sha256_update,
+		.fast_final_fn = git_hash_sha256_final,
+		.fast_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,