hash.h: scaffolding for _unsafe hashing variants

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>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/hash.h b/hash.h
index 72ffbc862e557a542c49e9afe9b7fb709d32b0a1..96458b129f9aec58a4513800a25e2d94dc28f581 100644 (file)
--- 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 440c5c68509f6dc47f65e41bcf0b243ce679cbf5..206ff625d9a50b798e8b5e18b1d7230453fc2390 100644 (file)
--- 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,