git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Taylor Blau <me@ttaylorr.com>
To: git@vger.kernel.org
Cc: Jeff King <peff@peff.net>,
	"brian m. carlson" <sandals@crustytoothpaste.net>,
	Elijah Newren <newren@gmail.com>, Patrick Steinhardt <ps@pks.im>,
	Junio C Hamano <gitster@pobox.com>
Subject: [PATCH 2/4] hash.h: scaffolding for _fast hashing variants
Date: Sun, 1 Sep 2024 12:03:24 -0400	[thread overview]
Message-ID: <6ac6f934c32bdc600cdb8d2a08d4aa390c1f2994.1725206584.git.me@ttaylorr.com> (raw)
In-Reply-To: <cover.1725206584.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 "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 --git a/hash.h b/hash.h
index 72ffbc862e5..f255e5c1e8a 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 hash initialization function. */
+	git_hash_init_fn fast_init_fn;
+
+	/* The fast hash context cloning function. */
+	git_hash_clone_fn fast_clone_fn;
+
+	/* The fast hash update function. */
+	git_hash_update_fn fast_update_fn;
+
+	/* The fast hash finalization function. */
+	git_hash_final_fn fast_final_fn;
+
+	/* The fast hash finalization function for object IDs. */
+	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,
-- 
2.46.0.425.ge8f5cbd280c


  parent reply	other threads:[~2024-09-01 16:03 UTC|newest]

Thread overview: 99+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-09-01 16:03 [PATCH 0/4] hash.h: support choosing a separate SHA-1 for non-cryptographic uses Taylor Blau
2024-09-01 16:03 ` [PATCH 1/4] sha1: do not redefine `platform_SHA_CTX` and friends Taylor Blau
2024-09-02 13:41   ` Patrick Steinhardt
2024-09-03 19:34     ` Taylor Blau
2024-09-01 16:03 ` Taylor Blau [this message]
2024-09-02 13:41   ` [PATCH 2/4] hash.h: scaffolding for _fast hashing variants Patrick Steinhardt
2024-09-03 17:27     ` Junio C Hamano
2024-09-03 19:52       ` Taylor Blau
2024-09-03 20:47         ` Junio C Hamano
2024-09-03 21:24           ` Taylor Blau
2024-09-04  7:05           ` Patrick Steinhardt
2024-09-04 14:53             ` Junio C Hamano
2024-09-03 19:40     ` Taylor Blau
2024-09-01 16:03 ` [PATCH 3/4] Makefile: allow specifying a SHA-1 for non-cryptographic uses Taylor Blau
2024-09-02 13:41   ` Patrick Steinhardt
2024-09-03 19:43     ` Taylor Blau
2024-09-01 16:03 ` [PATCH 4/4] csum-file.c: use fast SHA-1 implementation when available Taylor Blau
2024-09-02 13:41   ` Patrick Steinhardt
2024-09-03  1:22     ` brian m. carlson
2024-09-03 19:50     ` Taylor Blau
2024-09-02  3:41 ` [PATCH 0/4] hash.h: support choosing a separate SHA-1 for non-cryptographic uses Junio C Hamano
2024-09-03 19:48   ` Taylor Blau
2024-09-03 20:44     ` Junio C Hamano
2024-09-02 14:08 ` brian m. carlson
2024-09-03 19:47   ` Taylor Blau
2024-09-03 22:41     ` Junio C Hamano
2024-09-04 14:01     ` brian m. carlson
2024-09-05 10:37     ` Jeff King
2024-09-05 15:41       ` Junio C Hamano
2024-09-05 16:23         ` Taylor Blau
2024-09-05 16:51           ` Junio C Hamano
2024-09-05 17:04             ` Taylor Blau
2024-09-05 17:51               ` Taylor Blau
2024-09-05 20:21                 ` Taylor Blau
2024-09-05 20:27               ` Jeff King
2024-09-05 21:27                 ` Junio C Hamano
2024-09-05 15:11 ` [PATCH v2 " Taylor Blau
2024-09-05 15:12   ` [PATCH v2 1/4] sha1: do not redefine `platform_SHA_CTX` and friends Taylor Blau
2024-09-05 15:12   ` [PATCH v2 2/4] hash.h: scaffolding for _fast hashing variants Taylor Blau
2024-09-05 15:12   ` [PATCH v2 3/4] Makefile: allow specifying a SHA-1 for non-cryptographic uses Taylor Blau
2024-09-05 15:12   ` [PATCH v2 4/4] csum-file.c: use fast SHA-1 implementation when available Taylor Blau
2024-09-06 19:46 ` [PATCH v3 0/9] hash.h: support choosing a separate SHA-1 for non-cryptographic uses Taylor Blau
2024-09-06 19:46   ` [PATCH v3 1/9] finalize_object_file(): check for name collision before renaming Taylor Blau
2024-09-06 19:46   ` [PATCH v3 2/9] finalize_object_file(): refactor unlink_or_warn() placement Taylor Blau
2024-09-06 19:46   ` [PATCH v3 3/9] finalize_object_file(): implement collision check Taylor Blau
2024-09-06 21:44     ` Junio C Hamano
2024-09-06 21:51       ` Chris Torek
2024-09-10  6:53       ` Jeff King
2024-09-10 15:14         ` Junio C Hamano
2024-09-16 10:45     ` Patrick Steinhardt
2024-09-16 15:54       ` Taylor Blau
2024-09-16 16:03         ` Taylor Blau
2024-09-17 20:40       ` Junio C Hamano
2024-09-06 19:46   ` [PATCH v3 4/9] pack-objects: use finalize_object_file() to rename pack/idx/etc Taylor Blau
2024-09-06 19:46   ` [PATCH v3 5/9] i5500-git-daemon.sh: use compile-able version of Git without OpenSSL Taylor Blau
2024-09-11  6:10     ` Jeff King
2024-09-11  6:12       ` Jeff King
2024-09-12 20:28         ` Junio C Hamano
2024-09-11 15:28       ` Junio C Hamano
2024-09-11 21:23         ` Jeff King
2024-09-06 19:46   ` [PATCH v3 6/9] sha1: do not redefine `platform_SHA_CTX` and friends Taylor Blau
2024-09-06 19:46   ` [PATCH v3 7/9] hash.h: scaffolding for _fast hashing variants Taylor Blau
2024-09-06 19:46   ` [PATCH v3 8/9] Makefile: allow specifying a SHA-1 for non-cryptographic uses Taylor Blau
2024-09-06 19:46   ` [PATCH v3 9/9] csum-file.c: use fast SHA-1 implementation when available Taylor Blau
2024-09-06 21:50   ` [PATCH v3 0/9] hash.h: support choosing a separate SHA-1 for non-cryptographic uses Junio C Hamano
2024-09-24 17:32 ` [PATCH v4 0/8] " Taylor Blau
2024-09-24 17:32   ` [PATCH v4 1/8] finalize_object_file(): check for name collision before renaming Taylor Blau
2024-09-25 17:02     ` Junio C Hamano
2024-09-24 17:32   ` [PATCH v4 2/8] finalize_object_file(): refactor unlink_or_warn() placement Taylor Blau
2024-09-24 17:32   ` [PATCH v4 3/8] finalize_object_file(): implement collision check Taylor Blau
2024-09-24 20:37     ` Jeff King
2024-09-24 21:59       ` Taylor Blau
2024-09-24 22:20         ` Jeff King
2024-09-25 18:06           ` Taylor Blau
2024-09-24 21:32     ` Junio C Hamano
2024-09-24 22:02       ` Taylor Blau
2024-09-24 17:32   ` [PATCH v4 4/8] pack-objects: use finalize_object_file() to rename pack/idx/etc Taylor Blau
2024-09-24 21:34     ` Junio C Hamano
2024-09-24 17:32   ` [PATCH v4 5/8] sha1: do not redefine `platform_SHA_CTX` and friends Taylor Blau
2024-09-24 17:32   ` [PATCH v4 6/8] hash.h: scaffolding for _unsafe hashing variants Taylor Blau
2024-09-24 17:32   ` [PATCH v4 7/8] Makefile: allow specifying a SHA-1 for non-cryptographic uses Taylor Blau
2024-09-24 17:32   ` [PATCH v4 8/8] csum-file.c: use unsafe SHA-1 implementation when available Taylor Blau
2024-09-24 20:52   ` [PATCH v4 0/8] hash.h: support choosing a separate SHA-1 for non-cryptographic uses Jeff King
2024-09-25 16:58   ` Elijah Newren
2024-09-25 17:11     ` Junio C Hamano
2024-09-25 17:22       ` Taylor Blau
2024-09-25 17:22     ` Taylor Blau
2024-09-26 15:22 ` [PATCH v5 " Taylor Blau
2024-09-26 15:22   ` [PATCH v5 1/8] finalize_object_file(): check for name collision before renaming Taylor Blau
2024-09-26 15:22   ` [PATCH v5 2/8] finalize_object_file(): refactor unlink_or_warn() placement Taylor Blau
2024-09-26 15:22   ` [PATCH v5 3/8] finalize_object_file(): implement collision check Taylor Blau
2024-09-26 15:22   ` [PATCH v5 4/8] pack-objects: use finalize_object_file() to rename pack/idx/etc Taylor Blau
2024-09-26 15:22   ` [PATCH v5 5/8] sha1: do not redefine `platform_SHA_CTX` and friends Taylor Blau
2024-09-26 15:22   ` [PATCH v5 6/8] hash.h: scaffolding for _unsafe hashing variants Taylor Blau
2024-09-26 15:22   ` [PATCH v5 7/8] Makefile: allow specifying a SHA-1 for non-cryptographic uses Taylor Blau
2024-09-26 15:22   ` [PATCH v5 8/8] csum-file.c: use unsafe SHA-1 implementation when available Taylor Blau
2024-09-26 22:47   ` [PATCH v5 0/8] hash.h: support choosing a separate SHA-1 for non-cryptographic uses Elijah Newren
2024-09-27  0:44     ` Junio C Hamano
2024-09-27  3:57   ` Jeff King

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=6ac6f934c32bdc600cdb8d2a08d4aa390c1f2994.1725206584.git.me@ttaylorr.com \
    --to=me@ttaylorr.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=newren@gmail.com \
    --cc=peff@peff.net \
    --cc=ps@pks.im \
    --cc=sandals@crustytoothpaste.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).