From d74a4e57d2703e841deed994752b948a768f31ec Mon Sep 17 00:00:00 2001
From: Jeff King <peff@peff.net>
Date: Tue, 10 Jun 2014 17:39:35 -0400
Subject: sequencer: use logmsg_reencode in get_message

This simplifies the code, as logmsg_reencode handles the
reencoding for us in a single call. It also means we learn
logmsg_reencode's trick of pulling the buffer from disk when
commit->buffer is NULL (we currently just silently return!).
It is doubtful this matters in practice, though, as
sequencer operations would not generally turn off
save_commit_buffer.

Note that we may be fixing a bug here. The existing code
does:

  if (same_encoding(to, from))
	  reencode_string(buf, to, from);

That probably should have been "!same_encoding".

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 sequencer.c | 45 +++++----------------------------------------
 1 file changed, 5 insertions(+), 40 deletions(-)

(limited to 'sequencer.c')

diff --git a/sequencer.c b/sequencer.c
index bde5f047b0..2ee4f43035 100644
--- a/sequencer.c
+++ b/sequencer.c
@@ -116,39 +116,23 @@ static const char *action_name(const struct replay_opts *opts)
 	return opts->action == REPLAY_REVERT ? "revert" : "cherry-pick";
 }
 
-static char *get_encoding(const char *message);
-
 struct commit_message {
 	char *parent_label;
 	const char *label;
 	const char *subject;
-	char *reencoded_message;
 	const char *message;
 };
 
 static int get_message(struct commit *commit, struct commit_message *out)
 {
-	const char *encoding;
 	const char *abbrev, *subject;
 	int abbrev_len, subject_len;
 	char *q;
 
-	if (!commit->buffer)
-		return -1;
-	encoding = get_encoding(commit->buffer);
-	if (!encoding)
-		encoding = "UTF-8";
 	if (!git_commit_encoding)
 		git_commit_encoding = "UTF-8";
 
-	out->reencoded_message = NULL;
-	out->message = commit->buffer;
-	if (same_encoding(encoding, git_commit_encoding))
-		out->reencoded_message = reencode_string(commit->buffer,
-					git_commit_encoding, encoding);
-	if (out->reencoded_message)
-		out->message = out->reencoded_message;
-
+	out->message = logmsg_reencode(commit, NULL, git_commit_encoding);
 	abbrev = find_unique_abbrev(commit->object.sha1, DEFAULT_ABBREV);
 	abbrev_len = strlen(abbrev);
 
@@ -167,29 +151,10 @@ static int get_message(struct commit *commit, struct commit_message *out)
 	return 0;
 }
 
-static void free_message(struct commit_message *msg)
+static void free_message(struct commit *commit, struct commit_message *msg)
 {
 	free(msg->parent_label);
-	free(msg->reencoded_message);
-}
-
-static char *get_encoding(const char *message)
-{
-	const char *p = message, *eol;
-
-	while (*p && *p != '\n') {
-		for (eol = p + 1; *eol && *eol != '\n'; eol++)
-			; /* do nothing */
-		if (starts_with(p, "encoding ")) {
-			char *result = xmalloc(eol - 8 - p);
-			strlcpy(result, p + 9, eol - 8 - p);
-			return result;
-		}
-		p = eol;
-		if (*p == '\n')
-			p++;
-	}
-	return NULL;
+	logmsg_free(msg->message, commit);
 }
 
 static void write_cherry_pick_head(struct commit *commit, const char *pseudoref)
@@ -485,7 +450,7 @@ static int do_pick_commit(struct commit *commit, struct replay_opts *opts)
 	unsigned char head[20];
 	struct commit *base, *next, *parent;
 	const char *base_label, *next_label;
-	struct commit_message msg = { NULL, NULL, NULL, NULL, NULL };
+	struct commit_message msg = { NULL, NULL, NULL, NULL };
 	char *defmsg = NULL;
 	struct strbuf msgbuf = STRBUF_INIT;
 	int res, unborn = 0, allow;
@@ -650,7 +615,7 @@ static int do_pick_commit(struct commit *commit, struct replay_opts *opts)
 		res = run_git_commit(defmsg, opts, allow);
 
 leave:
-	free_message(&msg);
+	free_message(commit, &msg);
 	free(defmsg);
 
 	return res;
-- 
cgit v1.3


From b66103c3baa593a39b8b0751213b9fce60e94de4 Mon Sep 17 00:00:00 2001
From: Jeff King <peff@peff.net>
Date: Tue, 10 Jun 2014 17:41:39 -0400
Subject: convert logmsg_reencode to get_commit_buffer

Like the callsites in the previous commit, logmsg_reencode
already falls back to read_sha1_file when necessary.
However, I split its conversion out into its own commit
because it's a bit more complex.

We return either:

  1. The original commit->buffer

  2. A newly allocated buffer from read_sha1_file

  3. A reencoded buffer (based on either 1 or 2 above).

while trying to do as few extra reads/allocations as
possible. Callers currently free the result with
logmsg_free, but we can simplify this by pointing them
straight to unuse_commit_buffer. This is a slight layering
violation, in that we may be passing a buffer from (3).
However, since the end result is to free() anything except
(1), which is unlikely to change, and because this makes the
interface much simpler, it's a reasonable bending of the
rules.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 builtin/blame.c |  4 ++--
 builtin/reset.c |  2 +-
 commit.h        |  1 -
 pretty.c        | 40 +++++++++++-----------------------------
 revision.c      |  2 +-
 sequencer.c     |  2 +-
 6 files changed, 16 insertions(+), 35 deletions(-)

(limited to 'sequencer.c')

diff --git a/builtin/blame.c b/builtin/blame.c
index 38784ab9d6..857d98a324 100644
--- a/builtin/blame.c
+++ b/builtin/blame.c
@@ -1416,7 +1416,7 @@ static void get_commit_info(struct commit *commit,
 		    &ret->author_time, &ret->author_tz);
 
 	if (!detailed) {
-		logmsg_free(message, commit);
+		unuse_commit_buffer(commit, message);
 		return;
 	}
 
@@ -1430,7 +1430,7 @@ static void get_commit_info(struct commit *commit,
 	else
 		strbuf_addf(&ret->summary, "(%s)", sha1_to_hex(commit->object.sha1));
 
-	logmsg_free(message, commit);
+	unuse_commit_buffer(commit, message);
 }
 
 /*
diff --git a/builtin/reset.c b/builtin/reset.c
index b5312c4c65..6bd6245821 100644
--- a/builtin/reset.c
+++ b/builtin/reset.c
@@ -109,7 +109,7 @@ static void print_new_head_line(struct commit *commit)
 	}
 	else
 		printf("\n");
-	logmsg_free(msg, commit);
+	unuse_commit_buffer(commit, msg);
 }
 
 static void update_index_from_diff(struct diff_queue_struct *q,
diff --git a/commit.h b/commit.h
index 259c0aec75..5ce5ce72c3 100644
--- a/commit.h
+++ b/commit.h
@@ -156,7 +156,6 @@ struct rev_info; /* in revision.h, it circularly uses enum cmit_fmt */
 extern const char *logmsg_reencode(const struct commit *commit,
 				   char **commit_encoding,
 				   const char *output_encoding);
-extern void logmsg_free(const char *msg, const struct commit *commit);
 extern void get_commit_format(const char *arg, struct rev_info *);
 extern const char *format_subject(struct strbuf *sb, const char *msg,
 				  const char *line_separator);
diff --git a/pretty.c b/pretty.c
index 85b0bb3431..915bd1e2e9 100644
--- a/pretty.c
+++ b/pretty.c
@@ -613,22 +613,9 @@ const char *logmsg_reencode(const struct commit *commit,
 	static const char *utf8 = "UTF-8";
 	const char *use_encoding;
 	char *encoding;
-	char *msg = commit->buffer;
+	const char *msg = get_commit_buffer(commit);
 	char *out;
 
-	if (!msg) {
-		enum object_type type;
-		unsigned long size;
-
-		msg = read_sha1_file(commit->object.sha1, &type, &size);
-		if (!msg)
-			die("Cannot read commit object %s",
-			    sha1_to_hex(commit->object.sha1));
-		if (type != OBJ_COMMIT)
-			die("Expected commit for '%s', got %s",
-			    sha1_to_hex(commit->object.sha1), typename(type));
-	}
-
 	if (!output_encoding || !*output_encoding) {
 		if (commit_encoding)
 			*commit_encoding =
@@ -652,12 +639,13 @@ const char *logmsg_reencode(const struct commit *commit,
 		 * Otherwise, we still want to munge the encoding header in the
 		 * result, which will be done by modifying the buffer. If we
 		 * are using a fresh copy, we can reuse it. But if we are using
-		 * the cached copy from commit->buffer, we need to duplicate it
-		 * to avoid munging commit->buffer.
+		 * the cached copy from get_commit_buffer, we need to duplicate it
+		 * to avoid munging the cached copy.
 		 */
-		out = msg;
-		if (out == commit->buffer)
-			out = xstrdup(out);
+		if (msg == get_cached_commit_buffer(commit))
+			out = xstrdup(msg);
+		else
+			out = (char *)msg;
 	}
 	else {
 		/*
@@ -667,8 +655,8 @@ const char *logmsg_reencode(const struct commit *commit,
 		 * copy, we can free it.
 		 */
 		out = reencode_string(msg, output_encoding, use_encoding);
-		if (out && msg != commit->buffer)
-			free(msg);
+		if (out)
+			unuse_commit_buffer(commit, msg);
 	}
 
 	/*
@@ -687,12 +675,6 @@ const char *logmsg_reencode(const struct commit *commit,
 	return out ? out : msg;
 }
 
-void logmsg_free(const char *msg, const struct commit *commit)
-{
-	if (msg != commit->buffer)
-		free((void *)msg);
-}
-
 static int mailmap_name(const char **email, size_t *email_len,
 			const char **name, size_t *name_len)
 {
@@ -1531,7 +1513,7 @@ void format_commit_message(const struct commit *commit,
 	}
 
 	free(context.commit_encoding);
-	logmsg_free(context.message, commit);
+	unuse_commit_buffer(commit, context.message);
 	free(context.signature_check.gpg_output);
 	free(context.signature_check.signer);
 }
@@ -1767,7 +1749,7 @@ void pretty_print_commit(struct pretty_print_context *pp,
 	if (pp->fmt == CMIT_FMT_EMAIL && sb->len <= beginning_of_body)
 		strbuf_addch(sb, '\n');
 
-	logmsg_free(reencoded, commit);
+	unuse_commit_buffer(commit, reencoded);
 }
 
 void pp_commit_easy(enum cmit_fmt fmt, const struct commit *commit,
diff --git a/revision.c b/revision.c
index be151ef462..1cc91e5911 100644
--- a/revision.c
+++ b/revision.c
@@ -2844,7 +2844,7 @@ static int commit_match(struct commit *commit, struct rev_info *opt)
 		retval = grep_buffer(&opt->grep_filter,
 				     (char *)message, strlen(message));
 	strbuf_release(&buf);
-	logmsg_free(message, commit);
+	unuse_commit_buffer(commit, message);
 	return retval;
 }
 
diff --git a/sequencer.c b/sequencer.c
index 2ee4f43035..7b1f87af35 100644
--- a/sequencer.c
+++ b/sequencer.c
@@ -154,7 +154,7 @@ static int get_message(struct commit *commit, struct commit_message *out)
 static void free_message(struct commit *commit, struct commit_message *msg)
 {
 	free(msg->parent_label);
-	logmsg_free(msg->message, commit);
+	unuse_commit_buffer(commit, msg->message);
 }
 
 static void write_cherry_pick_head(struct commit *commit, const char *pseudoref)
-- 
cgit v1.3


From bc6b8fc1300ef79c4b4c3c2a79bb3c1e2e032963 Mon Sep 17 00:00:00 2001
From: Jeff King <peff@peff.net>
Date: Tue, 10 Jun 2014 17:41:51 -0400
Subject: use get_commit_buffer everywhere

Each of these sites assumes that commit->buffer is valid.
Since they would segfault if this was not the case, they are
likely to be correct in practice. However, we can
future-proof them by using get_commit_buffer.

And as a side effect, we abstract away the final bare uses
of commit->buffer.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 builtin/fast-export.c   |  5 ++++-
 builtin/fmt-merge-msg.c |  5 ++++-
 builtin/log.c           |  7 +++++--
 fsck.c                  | 13 +++++++++++--
 merge-recursive.c       |  4 +++-
 notes-merge.c           |  4 +++-
 sequencer.c             |  4 +++-
 7 files changed, 33 insertions(+), 9 deletions(-)

(limited to 'sequencer.c')

diff --git a/builtin/fast-export.c b/builtin/fast-export.c
index b8d8a3aaf9..7ee5e08442 100644
--- a/builtin/fast-export.c
+++ b/builtin/fast-export.c
@@ -279,6 +279,7 @@ static const char *find_encoding(const char *begin, const char *end)
 static void handle_commit(struct commit *commit, struct rev_info *rev)
 {
 	int saved_output_format = rev->diffopt.output_format;
+	const char *commit_buffer;
 	const char *author, *author_end, *committer, *committer_end;
 	const char *encoding, *message;
 	char *reencoded = NULL;
@@ -288,7 +289,8 @@ static void handle_commit(struct commit *commit, struct rev_info *rev)
 	rev->diffopt.output_format = DIFF_FORMAT_CALLBACK;
 
 	parse_commit_or_die(commit);
-	author = strstr(commit->buffer, "\nauthor ");
+	commit_buffer = get_commit_buffer(commit);
+	author = strstr(commit_buffer, "\nauthor ");
 	if (!author)
 		die ("Could not find author in commit %s",
 		     sha1_to_hex(commit->object.sha1));
@@ -335,6 +337,7 @@ static void handle_commit(struct commit *commit, struct rev_info *rev)
 			  ? strlen(message) : 0),
 	       reencoded ? reencoded : message ? message : "");
 	free(reencoded);
+	unuse_commit_buffer(commit, commit_buffer);
 
 	for (i = 0, p = commit->parents; p; p = p->next) {
 		int mark = get_object_mark(&p->item->object);
diff --git a/builtin/fmt-merge-msg.c b/builtin/fmt-merge-msg.c
index 3906eda877..01f6d59eef 100644
--- a/builtin/fmt-merge-msg.c
+++ b/builtin/fmt-merge-msg.c
@@ -230,12 +230,14 @@ static void add_branch_desc(struct strbuf *out, const char *name)
 static void record_person(int which, struct string_list *people,
 			  struct commit *commit)
 {
+	const char *buffer;
 	char *name_buf, *name, *name_end;
 	struct string_list_item *elem;
 	const char *field;
 
 	field = (which == 'a') ? "\nauthor " : "\ncommitter ";
-	name = strstr(commit->buffer, field);
+	buffer = get_commit_buffer(commit);
+	name = strstr(buffer, field);
 	if (!name)
 		return;
 	name += strlen(field);
@@ -247,6 +249,7 @@ static void record_person(int which, struct string_list *people,
 	if (name_end < name)
 		return;
 	name_buf = xmemdupz(name, name_end - name + 1);
+	unuse_commit_buffer(commit, buffer);
 
 	elem = string_list_lookup(people, name_buf);
 	if (!elem) {
diff --git a/builtin/log.c b/builtin/log.c
index 226f8f2980..2c742606bc 100644
--- a/builtin/log.c
+++ b/builtin/log.c
@@ -918,9 +918,12 @@ static void make_cover_letter(struct rev_info *rev, int use_stdout,
 	log_write_email_headers(rev, head, &pp.subject, &pp.after_subject,
 				&need_8bit_cte);
 
-	for (i = 0; !need_8bit_cte && i < nr; i++)
-		if (has_non_ascii(list[i]->buffer))
+	for (i = 0; !need_8bit_cte && i < nr; i++) {
+		const char *buf = get_commit_buffer(list[i]);
+		if (has_non_ascii(buf))
 			need_8bit_cte = 1;
+		unuse_commit_buffer(list[i], buf);
+	}
 
 	if (!branch_name)
 		branch_name = find_branch_name(rev);
diff --git a/fsck.c b/fsck.c
index abed62bac7..8223780592 100644
--- a/fsck.c
+++ b/fsck.c
@@ -276,9 +276,10 @@ static int fsck_ident(const char **ident, struct object *obj, fsck_error error_f
 	return 0;
 }
 
-static int fsck_commit(struct commit *commit, fsck_error error_func)
+static int fsck_commit_buffer(struct commit *commit, const char *buffer,
+			      fsck_error error_func)
 {
-	const char *buffer = commit->buffer, *tmp;
+	const char *tmp;
 	unsigned char tree_sha1[20], sha1[20];
 	struct commit_graft *graft;
 	int parents = 0;
@@ -336,6 +337,14 @@ static int fsck_commit(struct commit *commit, fsck_error error_func)
 	return 0;
 }
 
+static int fsck_commit(struct commit *commit, fsck_error error_func)
+{
+	const char *buffer = get_commit_buffer(commit);
+	int ret = fsck_commit_buffer(commit, buffer, error_func);
+	unuse_commit_buffer(commit, buffer);
+	return ret;
+}
+
 static int fsck_tag(struct tag *tag, fsck_error error_func)
 {
 	struct object *tagged = tag->tagged;
diff --git a/merge-recursive.c b/merge-recursive.c
index fc2a68a0d1..78908aaacc 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -190,9 +190,11 @@ static void output_commit_title(struct merge_options *o, struct commit *commit)
 			printf(_("(bad commit)\n"));
 		else {
 			const char *title;
-			int len = find_commit_subject(commit->buffer, &title);
+			const char *msg = get_commit_buffer(commit);
+			int len = find_commit_subject(msg, &title);
 			if (len)
 				printf("%.*s\n", len, title);
+			unuse_commit_buffer(commit, msg);
 		}
 	}
 }
diff --git a/notes-merge.c b/notes-merge.c
index 697cec349a..e804db2d02 100644
--- a/notes-merge.c
+++ b/notes-merge.c
@@ -672,7 +672,8 @@ int notes_merge_commit(struct notes_merge_options *o,
 	DIR *dir;
 	struct dirent *e;
 	struct strbuf path = STRBUF_INIT;
-	char *msg = strstr(partial_commit->buffer, "\n\n");
+	const char *buffer = get_commit_buffer(partial_commit);
+	const char *msg = strstr(buffer, "\n\n");
 	int baselen;
 
 	strbuf_addstr(&path, git_path(NOTES_MERGE_WORKTREE));
@@ -721,6 +722,7 @@ int notes_merge_commit(struct notes_merge_options *o,
 
 	create_notes_commit(partial_tree, partial_commit->parents,
 			    msg, strlen(msg), result_sha1);
+	unuse_commit_buffer(partial_commit, buffer);
 	if (o->verbosity >= 4)
 		printf("Finalized notes merge commit: %s\n",
 			sha1_to_hex(result_sha1));
diff --git a/sequencer.c b/sequencer.c
index 7b1f87af35..69bcf3d801 100644
--- a/sequencer.c
+++ b/sequencer.c
@@ -662,10 +662,12 @@ static int format_todo(struct strbuf *buf, struct commit_list *todo_list,
 	int subject_len;
 
 	for (cur = todo_list; cur; cur = cur->next) {
+		const char *commit_buffer = get_commit_buffer(cur->item);
 		sha1_abbrev = find_unique_abbrev(cur->item->object.sha1, DEFAULT_ABBREV);
-		subject_len = find_commit_subject(cur->item->buffer, &subject);
+		subject_len = find_commit_subject(commit_buffer, &subject);
 		strbuf_addf(buf, "%s %s %.*s\n", action_str, sha1_abbrev,
 			subject_len, subject);
+		unuse_commit_buffer(cur->item, commit_buffer);
 	}
 	return 0;
 }
-- 
cgit v1.3


From 8597ea3afea067b39ba7d4adae7ec6c1ee0e7c91 Mon Sep 17 00:00:00 2001
From: Jeff King <peff@peff.net>
Date: Tue, 10 Jun 2014 17:44:13 -0400
Subject: commit: record buffer length in cache

Most callsites which use the commit buffer try to use the
cached version attached to the commit, rather than
re-reading from disk. Unfortunately, that interface provides
only a pointer to the NUL-terminated buffer, with no
indication of the original length.

For the most part, this doesn't matter. People do not put
NULs in their commit messages, and the log code is happy to
treat it all as a NUL-terminated string. However, some code
paths do care. For example, when checking signatures, we
want to be very careful that we verify all the bytes to
avoid malicious trickery.

This patch just adds an optional "size" out-pointer to
get_commit_buffer and friends. The existing callers all pass
NULL (there did not seem to be any obvious sites where we
could avoid an immediate strlen() call, though perhaps with
some further refactoring we could).

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 builtin/blame.c         | 14 ++++++++++++-
 builtin/fast-export.c   |  2 +-
 builtin/fmt-merge-msg.c |  2 +-
 builtin/index-pack.c    |  2 +-
 builtin/log.c           |  2 +-
 builtin/rev-list.c      |  2 +-
 commit.c                | 54 ++++++++++++++++++++++++++++++++-----------------
 commit.h                |  8 ++++----
 fsck.c                  |  2 +-
 log-tree.c              |  2 +-
 merge-recursive.c       |  2 +-
 notes-merge.c           |  2 +-
 object.c                |  4 ++--
 pretty.c                |  4 ++--
 sequencer.c             |  2 +-
 sha1_name.c             |  2 +-
 16 files changed, 68 insertions(+), 38 deletions(-)

(limited to 'sequencer.c')

diff --git a/builtin/blame.c b/builtin/blame.c
index 857d98a324..b84e375b5c 100644
--- a/builtin/blame.c
+++ b/builtin/blame.c
@@ -1998,6 +1998,18 @@ static void append_merge_parents(struct commit_list **tail)
 	strbuf_release(&line);
 }
 
+/*
+ * This isn't as simple as passing sb->buf and sb->len, because we
+ * want to transfer ownership of the buffer to the commit (so we
+ * must use detach).
+ */
+static void set_commit_buffer_from_strbuf(struct commit *c, struct strbuf *sb)
+{
+	size_t len;
+	void *buf = strbuf_detach(sb, &len);
+	set_commit_buffer(c, buf, len);
+}
+
 /*
  * Prepare a dummy commit that represents the work tree (or staged) item.
  * Note that annotating work tree item never works in the reverse.
@@ -2046,7 +2058,7 @@ static struct commit *fake_working_tree_commit(struct diff_options *opt,
 		    ident, ident, path,
 		    (!contents_from ? path :
 		     (!strcmp(contents_from, "-") ? "standard input" : contents_from)));
-	set_commit_buffer(commit, strbuf_detach(&msg, NULL));
+	set_commit_buffer_from_strbuf(commit, &msg);
 
 	if (!contents_from || strcmp("-", contents_from)) {
 		struct stat st;
diff --git a/builtin/fast-export.c b/builtin/fast-export.c
index 7ee5e08442..05d161f19f 100644
--- a/builtin/fast-export.c
+++ b/builtin/fast-export.c
@@ -289,7 +289,7 @@ static void handle_commit(struct commit *commit, struct rev_info *rev)
 	rev->diffopt.output_format = DIFF_FORMAT_CALLBACK;
 
 	parse_commit_or_die(commit);
-	commit_buffer = get_commit_buffer(commit);
+	commit_buffer = get_commit_buffer(commit, NULL);
 	author = strstr(commit_buffer, "\nauthor ");
 	if (!author)
 		die ("Could not find author in commit %s",
diff --git a/builtin/fmt-merge-msg.c b/builtin/fmt-merge-msg.c
index 01f6d59eef..ef8b254ef2 100644
--- a/builtin/fmt-merge-msg.c
+++ b/builtin/fmt-merge-msg.c
@@ -236,7 +236,7 @@ static void record_person(int which, struct string_list *people,
 	const char *field;
 
 	field = (which == 'a') ? "\nauthor " : "\ncommitter ";
-	buffer = get_commit_buffer(commit);
+	buffer = get_commit_buffer(commit, NULL);
 	name = strstr(buffer, field);
 	if (!name)
 		return;
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index 42551ce4ff..459b9f07bb 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -774,7 +774,7 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
 			}
 			if (obj->type == OBJ_COMMIT) {
 				struct commit *commit = (struct commit *) obj;
-				if (detach_commit_buffer(commit) != data)
+				if (detach_commit_buffer(commit, NULL) != data)
 					die("BUG: parse_object_buffer transmogrified our buffer");
 			}
 			obj->flags |= FLAG_CHECKED;
diff --git a/builtin/log.c b/builtin/log.c
index 2c742606bc..c599eacf72 100644
--- a/builtin/log.c
+++ b/builtin/log.c
@@ -919,7 +919,7 @@ static void make_cover_letter(struct rev_info *rev, int use_stdout,
 				&need_8bit_cte);
 
 	for (i = 0; !need_8bit_cte && i < nr; i++) {
-		const char *buf = get_commit_buffer(list[i]);
+		const char *buf = get_commit_buffer(list[i], NULL);
 		if (has_non_ascii(buf))
 			need_8bit_cte = 1;
 		unuse_commit_buffer(list[i], buf);
diff --git a/builtin/rev-list.c b/builtin/rev-list.c
index 3fcbf21c03..ff84a825ff 100644
--- a/builtin/rev-list.c
+++ b/builtin/rev-list.c
@@ -106,7 +106,7 @@ static void show_commit(struct commit *commit, void *data)
 	else
 		putchar('\n');
 
-	if (revs->verbose_header && get_cached_commit_buffer(commit)) {
+	if (revs->verbose_header && get_cached_commit_buffer(commit, NULL)) {
 		struct strbuf buf = STRBUF_INIT;
 		struct pretty_print_context ctx = {0};
 		ctx.abbrev = revs->abbrev;
diff --git a/commit.c b/commit.c
index e289c78327..a036e181c7 100644
--- a/commit.c
+++ b/commit.c
@@ -245,22 +245,31 @@ int unregister_shallow(const unsigned char *sha1)
 	return 0;
 }
 
-define_commit_slab(buffer_slab, void *);
+struct commit_buffer {
+	void *buffer;
+	unsigned long size;
+};
+define_commit_slab(buffer_slab, struct commit_buffer);
 static struct buffer_slab buffer_slab = COMMIT_SLAB_INIT(1, buffer_slab);
 
-void set_commit_buffer(struct commit *commit, void *buffer)
+void set_commit_buffer(struct commit *commit, void *buffer, unsigned long size)
 {
-	*buffer_slab_at(&buffer_slab, commit) = buffer;
+	struct commit_buffer *v = buffer_slab_at(&buffer_slab, commit);
+	v->buffer = buffer;
+	v->size = size;
 }
 
-const void *get_cached_commit_buffer(const struct commit *commit)
+const void *get_cached_commit_buffer(const struct commit *commit, unsigned long *sizep)
 {
-	return *buffer_slab_at(&buffer_slab, commit);
+	struct commit_buffer *v = buffer_slab_at(&buffer_slab, commit);
+	if (sizep)
+		*sizep = v->size;
+	return v->buffer;
 }
 
-const void *get_commit_buffer(const struct commit *commit)
+const void *get_commit_buffer(const struct commit *commit, unsigned long *sizep)
 {
-	const void *ret = get_cached_commit_buffer(commit);
+	const void *ret = get_cached_commit_buffer(commit, sizep);
 	if (!ret) {
 		enum object_type type;
 		unsigned long size;
@@ -271,29 +280,38 @@ const void *get_commit_buffer(const struct commit *commit)
 		if (type != OBJ_COMMIT)
 			die("expected commit for %s, got %s",
 			    sha1_to_hex(commit->object.sha1), typename(type));
+		if (sizep)
+			*sizep = size;
 	}
 	return ret;
 }
 
 void unuse_commit_buffer(const struct commit *commit, const void *buffer)
 {
-	void *cached = *buffer_slab_at(&buffer_slab, commit);
-	if (cached != buffer)
+	struct commit_buffer *v = buffer_slab_at(&buffer_slab, commit);
+	if (v->buffer != buffer)
 		free((void *)buffer);
 }
 
 void free_commit_buffer(struct commit *commit)
 {
-	void **b = buffer_slab_at(&buffer_slab, commit);
-	free(*b);
-	*b = NULL;
+	struct commit_buffer *v = buffer_slab_at(&buffer_slab, commit);
+	free(v->buffer);
+	v->buffer = NULL;
+	v->size = 0;
 }
 
-const void *detach_commit_buffer(struct commit *commit)
+const void *detach_commit_buffer(struct commit *commit, unsigned long *sizep)
 {
-	void **b = buffer_slab_at(&buffer_slab, commit);
-	void *ret = *b;
-	*b = NULL;
+	struct commit_buffer *v = buffer_slab_at(&buffer_slab, commit);
+	void *ret;
+
+	ret = v->buffer;
+	if (sizep)
+		*sizep = v->size;
+
+	v->buffer = NULL;
+	v->size = 0;
 	return ret;
 }
 
@@ -374,7 +392,7 @@ int parse_commit(struct commit *item)
 	}
 	ret = parse_commit_buffer(item, buffer, size);
 	if (save_commit_buffer && !ret) {
-		set_commit_buffer(item, buffer);
+		set_commit_buffer(item, buffer, size);
 		return 0;
 	}
 	free(buffer);
@@ -589,7 +607,7 @@ static void record_author_date(struct author_date_slab *author_date,
 			       struct commit *commit)
 {
 	const char *buf, *line_end, *ident_line;
-	const char *buffer = get_commit_buffer(commit);
+	const char *buffer = get_commit_buffer(commit, NULL);
 	struct ident_split ident;
 	char *date_end;
 	unsigned long date;
diff --git a/commit.h b/commit.h
index e1c25692f1..61559a9d45 100644
--- a/commit.h
+++ b/commit.h
@@ -54,20 +54,20 @@ void parse_commit_or_die(struct commit *item);
  * Associate an object buffer with the commit. The ownership of the
  * memory is handed over to the commit, and must be free()-able.
  */
-void set_commit_buffer(struct commit *, void *buffer);
+void set_commit_buffer(struct commit *, void *buffer, unsigned long size);
 
 /*
  * Get any cached object buffer associated with the commit. Returns NULL
  * if none. The resulting memory should not be freed.
  */
-const void *get_cached_commit_buffer(const struct commit *);
+const void *get_cached_commit_buffer(const struct commit *, unsigned long *size);
 
 /*
  * Get the commit's object contents, either from cache or by reading the object
  * from disk. The resulting memory should not be modified, and must be given
  * to unuse_commit_buffer when the caller is done.
  */
-const void *get_commit_buffer(const struct commit *);
+const void *get_commit_buffer(const struct commit *, unsigned long *size);
 
 /*
  * Tell the commit subsytem that we are done with a particular commit buffer.
@@ -86,7 +86,7 @@ void free_commit_buffer(struct commit *);
  * Disassociate any cached object buffer from the commit, but do not free it.
  * The buffer (or NULL, if none) is returned.
  */
-const void *detach_commit_buffer(struct commit *);
+const void *detach_commit_buffer(struct commit *, unsigned long *sizep);
 
 /* Find beginning and length of commit subject. */
 int find_commit_subject(const char *commit_buffer, const char **subject);
diff --git a/fsck.c b/fsck.c
index 8223780592..a7233c8d0b 100644
--- a/fsck.c
+++ b/fsck.c
@@ -339,7 +339,7 @@ static int fsck_commit_buffer(struct commit *commit, const char *buffer,
 
 static int fsck_commit(struct commit *commit, fsck_error error_func)
 {
-	const char *buffer = get_commit_buffer(commit);
+	const char *buffer = get_commit_buffer(commit, NULL);
 	int ret = fsck_commit_buffer(commit, buffer, error_func);
 	unuse_commit_buffer(commit, buffer);
 	return ret;
diff --git a/log-tree.c b/log-tree.c
index e9ef8abd37..444702163a 100644
--- a/log-tree.c
+++ b/log-tree.c
@@ -588,7 +588,7 @@ void show_log(struct rev_info *opt)
 		show_mergetag(opt, commit);
 	}
 
-	if (!get_cached_commit_buffer(commit))
+	if (!get_cached_commit_buffer(commit, NULL))
 		return;
 
 	if (opt->show_notes) {
diff --git a/merge-recursive.c b/merge-recursive.c
index 78908aaacc..a9ab328923 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -190,7 +190,7 @@ static void output_commit_title(struct merge_options *o, struct commit *commit)
 			printf(_("(bad commit)\n"));
 		else {
 			const char *title;
-			const char *msg = get_commit_buffer(commit);
+			const char *msg = get_commit_buffer(commit, NULL);
 			int len = find_commit_subject(msg, &title);
 			if (len)
 				printf("%.*s\n", len, title);
diff --git a/notes-merge.c b/notes-merge.c
index e804db2d02..fd5fae255d 100644
--- a/notes-merge.c
+++ b/notes-merge.c
@@ -672,7 +672,7 @@ int notes_merge_commit(struct notes_merge_options *o,
 	DIR *dir;
 	struct dirent *e;
 	struct strbuf path = STRBUF_INIT;
-	const char *buffer = get_commit_buffer(partial_commit);
+	const char *buffer = get_commit_buffer(partial_commit, NULL);
 	const char *msg = strstr(buffer, "\n\n");
 	int baselen;
 
diff --git a/object.c b/object.c
index 67b6e3533d..9c31e9a5e0 100644
--- a/object.c
+++ b/object.c
@@ -197,8 +197,8 @@ struct object *parse_object_buffer(const unsigned char *sha1, enum object_type t
 		if (commit) {
 			if (parse_commit_buffer(commit, buffer, size))
 				return NULL;
-			if (!get_cached_commit_buffer(commit)) {
-				set_commit_buffer(commit, buffer);
+			if (!get_cached_commit_buffer(commit, NULL)) {
+				set_commit_buffer(commit, buffer, size);
 				*eaten_p = 1;
 			}
 			obj = &commit->object;
diff --git a/pretty.c b/pretty.c
index 915bd1e2e9..b9fceedbb9 100644
--- a/pretty.c
+++ b/pretty.c
@@ -613,7 +613,7 @@ const char *logmsg_reencode(const struct commit *commit,
 	static const char *utf8 = "UTF-8";
 	const char *use_encoding;
 	char *encoding;
-	const char *msg = get_commit_buffer(commit);
+	const char *msg = get_commit_buffer(commit, NULL);
 	char *out;
 
 	if (!output_encoding || !*output_encoding) {
@@ -642,7 +642,7 @@ const char *logmsg_reencode(const struct commit *commit,
 		 * the cached copy from get_commit_buffer, we need to duplicate it
 		 * to avoid munging the cached copy.
 		 */
-		if (msg == get_cached_commit_buffer(commit))
+		if (msg == get_cached_commit_buffer(commit, NULL))
 			out = xstrdup(msg);
 		else
 			out = (char *)msg;
diff --git a/sequencer.c b/sequencer.c
index 69bcf3d801..bbaddcb05a 100644
--- a/sequencer.c
+++ b/sequencer.c
@@ -662,7 +662,7 @@ static int format_todo(struct strbuf *buf, struct commit_list *todo_list,
 	int subject_len;
 
 	for (cur = todo_list; cur; cur = cur->next) {
-		const char *commit_buffer = get_commit_buffer(cur->item);
+		const char *commit_buffer = get_commit_buffer(cur->item, NULL);
 		sha1_abbrev = find_unique_abbrev(cur->item->object.sha1, DEFAULT_ABBREV);
 		subject_len = find_commit_subject(commit_buffer, &subject);
 		strbuf_addf(buf, "%s %s %.*s\n", action_str, sha1_abbrev,
diff --git a/sha1_name.c b/sha1_name.c
index 0a65d234de..c2c938c4e1 100644
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -869,7 +869,7 @@ static int get_sha1_oneline(const char *prefix, unsigned char *sha1,
 		commit = pop_most_recent_commit(&list, ONELINE_SEEN);
 		if (!parse_object(commit->object.sha1))
 			continue;
-		buf = get_commit_buffer(commit);
+		buf = get_commit_buffer(commit, NULL);
 		p = strstr(buf, "\n\n");
 		matches = p && !regexec(&regex, p + 2, 0, NULL, 0);
 		unuse_commit_buffer(commit, buf);
-- 
cgit v1.3