Merge branch 'jk/commit-buffer-length' into maint

A handful of code paths had to read the commit object more than
once when showing header fields that are usually not parsed.  The
internal data structure to keep track of the contents of the commit
object has been updated to reduce the need for this double-reading,
and to allow the caller find the length of the object.

* jk/commit-buffer-length:
  reuse cached commit buffer when parsing signatures
  commit: record buffer length in cache
  commit: convert commit->buffer to a slab
  commit-slab: provide a static initializer
  use get_commit_buffer everywhere
  convert logmsg_reencode to get_commit_buffer
  use get_commit_buffer to avoid duplicate code
  use get_cached_commit_buffer where appropriate
  provide helpers to access the commit buffer
  provide a helper to set the commit buffer
  provide a helper to free commit buffer
  sequencer: use logmsg_reencode in get_message
  logmsg_reencode: return const buffer
  do not create "struct commit" with xcalloc
  commit: push commit_index update into alloc_commit_node
  alloc: include any-object allocations in alloc_report
  replace dangerous uses of strbuf_attach
  commit_tree: take a pointer/len pair rather than a const strbuf

27 files changed, 284 insertions, 197 deletions

diff --git a/alloc.c b/alloc.c
index f3ee745695..eb22a45c9d 100644
--- a/alloc.c
+++ b/alloc.c
@@ -47,23 +47,32 @@ union any_object {
 
 DEFINE_ALLOCATOR(blob, struct blob)
 DEFINE_ALLOCATOR(tree, struct tree)
-DEFINE_ALLOCATOR(commit, struct commit)
+DEFINE_ALLOCATOR(raw_commit, struct commit)
 DEFINE_ALLOCATOR(tag, struct tag)
 DEFINE_ALLOCATOR(object, union any_object)
 
+void *alloc_commit_node(void)
+{
+	static int commit_count;
+	struct commit *c = alloc_raw_commit_node();
+	c->index = commit_count++;
+	return c;
+}
+
 static void report(const char *name, unsigned int count, size_t size)
 {
 	fprintf(stderr, "%10s: %8u (%"PRIuMAX" kB)\n",
 			name, count, (uintmax_t) size);
 }
 
-#define REPORT(name)	\
-    report(#name, name##_allocs, name##_allocs * sizeof(struct name) >> 10)
+#define REPORT(name, type)	\
+    report(#name, name##_allocs, name##_allocs * sizeof(type) >> 10)
 
 void alloc_report(void)
 {
-	REPORT(blob);
-	REPORT(tree);
-	REPORT(commit);
-	REPORT(tag);
+	REPORT(blob, struct blob);
+	REPORT(tree, struct tree);
+	REPORT(raw_commit, struct commit);
+	REPORT(tag, struct tag);
+	REPORT(object, union any_object);
 }
diff --git a/builtin/blame.c b/builtin/blame.c
index d8b276048e..ef7cb1d254 100644
--- a/builtin/blame.c
+++ b/builtin/blame.c
@@ -1405,7 +1405,7 @@ static void get_commit_info(struct commit *commit,
 {
 	int len;
 	const char *subject, *encoding;
-	char *message;
+	const char *message;
 
 	commit_info_init(ret);
 
@@ -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);
 }
 
 /*
@@ -2006,6 +2006,18 @@ static void append_merge_parents(struct commit_list **tail)
 }
 
 /*
+ * 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.
  */
@@ -2026,7 +2038,7 @@ static struct commit *fake_working_tree_commit(struct diff_options *opt,
 	struct strbuf msg = STRBUF_INIT;
 
 	time(&now);
-	commit = xcalloc(1, sizeof(*commit));
+	commit = alloc_commit_node();
 	commit->object.parsed = 1;
 	commit->date = now;
 	commit->object.type = OBJ_COMMIT;
@@ -2053,7 +2065,7 @@ static struct commit *fake_working_tree_commit(struct diff_options *opt,
 		    ident, ident, path,
 		    (!contents_from ? path :
 		     (!strcmp(contents_from, "-") ? "standard input" : contents_from)));
-	commit->buffer = strbuf_detach(&msg, NULL);
+	set_commit_buffer_from_strbuf(commit, &msg);
 
 	if (!contents_from || strcmp("-", contents_from)) {
 		struct stat st;
diff --git a/builtin/commit-tree.c b/builtin/commit-tree.c
index 987a4c3d73..8a66c74e0f 100644
--- a/builtin/commit-tree.c
+++ b/builtin/commit-tree.c
@@ -123,8 +123,8 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix)
 			die_errno("git commit-tree: failed to read");
 	}
 
-	if (commit_tree(&buffer, tree_sha1, parents, commit_sha1,
-			NULL, sign_commit)) {
+	if (commit_tree(buffer.buf, buffer.len, tree_sha1, parents,
+			commit_sha1, NULL, sign_commit)) {
 		strbuf_release(&buffer);
 		return 1;
 	}
diff --git a/builtin/commit.c b/builtin/commit.c
index 12afc42d19..39cf8976e3 100644
--- a/builtin/commit.c
+++ b/builtin/commit.c
@@ -1672,8 +1672,8 @@ int cmd_commit(int argc, const char **argv, const char *prefix)
 		append_merge_tag_headers(parents, &tail);
 	}
 
-	if (commit_tree_extended(&sb, active_cache_tree->sha1, parents, sha1,
-				 author_ident.buf, sign_commit, extra)) {
+	if (commit_tree_extended(sb.buf, sb.len, active_cache_tree->sha1,
+			 parents, sha1, author_ident.buf, sign_commit, extra)) {
 		rollback_index_files();
 		die(_("failed to write commit object"));
 	}
diff --git a/builtin/fast-export.c b/builtin/fast-export.c
index b8d8a3aaf9..05d161f19f 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, NULL);
+	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..ef8b254ef2 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, NULL);
+	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/fsck.c b/builtin/fsck.c
index fc150c8821..8aadca160e 100644
--- a/builtin/fsck.c
+++ b/builtin/fsck.c
@@ -310,8 +310,7 @@ static int fsck_obj(struct object *obj)
 	if (obj->type == OBJ_COMMIT) {
 		struct commit *commit = (struct commit *) obj;
 
-		free(commit->buffer);
-		commit->buffer = NULL;
+		free_commit_buffer(commit);
 
 		if (!commit->parents && show_root)
 			printf("root %s\n", sha1_to_hex(commit->object.sha1));
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index 18f57de58b..8b3bd29dbc 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -786,7 +786,8 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
 			}
 			if (obj->type == OBJ_COMMIT) {
 				struct commit *commit = (struct commit *) obj;
-				commit->buffer = NULL;
+				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 3b6a6bbadd..4f678136d1 100644
--- a/builtin/log.c
+++ b/builtin/log.c
@@ -345,8 +345,7 @@ static int cmd_log_walk(struct rev_info *rev)
 			rev->max_count++;
 		if (!rev->reflog_info) {
 			/* we allow cycles in reflog ancestry */
-			free(commit->buffer);
-			commit->buffer = NULL;
+			free_commit_buffer(commit);
 		}
 		free_commit_list(commit->parents);
 		commit->parents = NULL;
@@ -915,9 +914,12 @@ 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], NULL);
+		if (has_non_ascii(buf))
 			need_8bit_cte = 1;
+		unuse_commit_buffer(list[i], buf);
+	}
 
 	if (!branch_name)
 		branch_name = find_branch_name(rev);
@@ -1504,8 +1506,7 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 		    reopen_stdout(rev.numbered_files ? NULL : commit, NULL, &rev, quiet))
 			die(_("Failed to create output files"));
 		shown = log_tree_commit(&rev, commit);
-		free(commit->buffer);
-		commit->buffer = NULL;
+		free_commit_buffer(commit);
 
 		/* We put one extra blank line between formatted
 		 * patches and this flag is used by log-tree code
diff --git a/builtin/merge.c b/builtin/merge.c
index 66d8843301..8763b2efa2 100644
--- a/builtin/merge.c
+++ b/builtin/merge.c
@@ -852,8 +852,8 @@ static int merge_trivial(struct commit *head, struct commit_list *remoteheads)
 	parent->next->item = remoteheads->item;
 	parent->next->next = NULL;
 	prepare_to_commit(remoteheads);
-	if (commit_tree(&merge_msg, result_tree, parent, result_commit, NULL,
-			sign_commit))
+	if (commit_tree(merge_msg.buf, merge_msg.len, result_tree, parent,
+			result_commit, NULL, sign_commit))
 		die(_("failed to write commit object"));
 	finish(head, remoteheads, result_commit, "In-index merge");
 	drop_save();
@@ -877,8 +877,8 @@ static int finish_automerge(struct commit *head,
 		commit_list_insert(head, &parents);
 	strbuf_addch(&merge_msg, '\n');
 	prepare_to_commit(remoteheads);
-	if (commit_tree(&merge_msg, result_tree, parents, result_commit,
-			NULL, sign_commit))
+	if (commit_tree(merge_msg.buf, merge_msg.len, result_tree, parents,
+			result_commit, NULL, sign_commit))
 		die(_("failed to write commit object"));
 	strbuf_addf(&buf, "Merge made by the '%s' strategy.", wt_strategy);
 	finish(head, remoteheads, result_commit, buf.buf);
diff --git a/builtin/reset.c b/builtin/reset.c
index f4e087596b..6bd6245821 100644
--- a/builtin/reset.c
+++ b/builtin/reset.c
@@ -93,7 +93,7 @@ static int reset_index(const unsigned char *sha1, int reset_type, int quiet)
 static void print_new_head_line(struct commit *commit)
 {
 	const char *hex, *body;
-	char *msg;
+	const char *msg;
 
 	hex = find_unique_abbrev(commit->object.sha1, DEFAULT_ABBREV);
 	printf(_("HEAD is now at %s"), hex);
@@ -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/builtin/rev-list.c b/builtin/rev-list.c
index 9f92905379..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 && commit->buffer) {
+	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;
@@ -173,8 +173,7 @@ static void finish_commit(struct commit *commit, void *data)
 		free_commit_list(commit->parents);
 		commit->parents = NULL;
 	}
-	free(commit->buffer);
-	commit->buffer = NULL;
+	free_commit_buffer(commit);
 }
 
 static void finish_object(struct object *obj,
diff --git a/commit-slab.h b/commit-slab.h
index cc114b53b0..375c9c751a 100644
--- a/commit-slab.h
+++ b/commit-slab.h
@@ -117,4 +117,16 @@ static int stat_ ##slabname## realloc
  * catch because GCC silently parses it by default.
  */
 
+/*
+ * Statically initialize a commit slab named "var". Note that this
+ * evaluates "stride" multiple times! Example:
+ *
+ *   struct indegree indegrees = COMMIT_SLAB_INIT(1, indegrees);
+ *
+ */
+#define COMMIT_SLAB_INIT(stride, var) { \
+	COMMIT_SLAB_SIZE / sizeof(**((var).slab)) / (stride), \
+	(stride), 0, NULL \
+}
+
 #endif /* COMMIT_SLAB_H */
diff --git a/commit.c b/commit.c
index f4793316a2..ebd7ad8465 100644
--- a/commit.c
+++ b/commit.c
@@ -17,7 +17,6 @@ static struct commit_extra_header *read_commit_extra_header_lines(const char *bu
 int save_commit_buffer = 1;
 
 const char *commit_type = "commit";
-static int commit_count;
 
 static struct commit *check_commit(struct object *obj,
 				   const unsigned char *sha1,
@@ -64,7 +63,6 @@ struct commit *lookup_commit(const unsigned char *sha1)
 	struct object *obj = lookup_object(sha1);
 	if (!obj) {
 		struct commit *c = alloc_commit_node();
-		c->index = commit_count++;
 		return create_object(sha1, OBJ_COMMIT, c);
 	}
 	if (!obj->type)
@@ -247,6 +245,76 @@ int unregister_shallow(const unsigned char *sha1)
 	return 0;
 }
 
+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, unsigned long size)
+{
+	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, unsigned long *sizep)
+{
+	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, unsigned long *sizep)
+{
+	const void *ret = get_cached_commit_buffer(commit, sizep);
+	if (!ret) {
+		enum object_type type;
+		unsigned long size;
+		ret = read_sha1_file(commit->object.sha1, &type, &size);
+		if (!ret)
+			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 (sizep)
+			*sizep = size;
+	}
+	return ret;
+}
+
+void unuse_commit_buffer(const struct commit *commit, const void *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)
+{
+	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, unsigned long *sizep)
+{
+	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;
+}
+
 int parse_commit_buffer(struct commit *item, const void *buffer, unsigned long size)
 {
 	const char *tail = buffer;
@@ -324,7 +392,7 @@ int parse_commit(struct commit *item)
 	}
 	ret = parse_commit_buffer(item, buffer, size);
 	if (save_commit_buffer && !ret) {
-		item->buffer = buffer;
+		set_commit_buffer(item, buffer, size);
 		return 0;
 	}
 	free(buffer);
@@ -539,22 +607,12 @@ static void record_author_date(struct author_date_slab *author_date,
 			       struct commit *commit)
 {
 	const char *buf, *line_end, *ident_line;
-	char *buffer = NULL;
+	const char *buffer = get_commit_buffer(commit, NULL);
 	struct ident_split ident;
 	char *date_end;
 	unsigned long date;
 
-	if (!commit->buffer) {
-		unsigned long size;
-		enum object_type type;
-		buffer = read_sha1_file(commit->object.sha1, &type, &size);
-		if (!buffer)
-			return;
-	}
-
-	for (buf = commit->buffer ? commit->buffer : buffer;
-	     buf;
-	     buf = line_end + 1) {
+	for (buf = buffer; buf; buf = line_end + 1) {
 		line_end = strchrnul(buf, '\n');
 		ident_line = skip_prefix(buf, "author ");
 		if (!ident_line) {
@@ -575,7 +633,7 @@ static void record_author_date(struct author_date_slab *author_date,
 	*(author_date_slab_at(author_date, commit)) = date;
 
 fail_exit:
-	free(buffer);
+	unuse_commit_buffer(commit, buffer);
 }
 
 static int compare_commits_by_author_date(const void *a_, const void *b_,
@@ -1080,17 +1138,14 @@ static int do_sign_commit(struct strbuf *buf, const char *keyid)
 	return 0;
 }
 
-int parse_signed_commit(const unsigned char *sha1,
+int parse_signed_commit(const struct commit *commit,
 			struct strbuf *payload, struct strbuf *signature)
 {
+
 	unsigned long size;
-	enum object_type type;
-	char *buffer = read_sha1_file(sha1, &type, &size);
+	const char *buffer = get_commit_buffer(commit, &size);
 	int in_signature, saw_signature = -1;
-	char *line, *tail;
-
-	if (!buffer || type != OBJ_COMMIT)
-		goto cleanup;
+	const char *line, *tail;
 
 	line = buffer;
 	tail = buffer + size;
@@ -1098,7 +1153,7 @@ int parse_signed_commit(const unsigned char *sha1,
 	saw_signature = 0;
 	while (line < tail) {
 		const char *sig = NULL;
-		char *next = memchr(line, '\n', tail - line);
+		const char *next = memchr(line, '\n', tail - line);
 
 		next = next ? next + 1 : tail;
 		if (in_signature && line[0] == ' ')
@@ -1119,8 +1174,7 @@ int parse_signed_commit(const unsigned char *sha1,
 		}
 		line = next;
 	}
- cleanup:
-	free(buffer);
+	unuse_commit_buffer(commit, buffer);
 	return saw_signature;
 }
 
@@ -1211,8 +1265,7 @@ void check_commit_signature(const struct commit* commit, struct signature_check
 
 	sigc->result = 'N';
 
-	if (parse_signed_commit(commit->object.sha1,
-				&payload, &signature) <= 0)
+	if (parse_signed_commit(commit, &payload, &signature) <= 0)
 		goto out;
 	status = verify_signed_buffer(payload.buf, payload.len,
 				      signature.buf, signature.len,
@@ -1257,11 +1310,9 @@ struct commit_extra_header *read_commit_extra_headers(struct commit *commit,
 {
 	struct commit_extra_header *extra = NULL;
 	unsigned long size;
-	enum object_type type;
-	char *buffer = read_sha1_file(commit->object.sha1, &type, &size);
-	if (buffer && type == OBJ_COMMIT)
-		extra = read_commit_extra_header_lines(buffer, size, exclude);
-	free(buffer);
+	const char *buffer = get_commit_buffer(commit, &size);
+	extra = read_commit_extra_header_lines(buffer, size, exclude);
+	unuse_commit_buffer(commit, buffer);
 	return extra;
 }
 
@@ -1344,7 +1395,8 @@ void free_commit_extra_headers(struct commit_extra_header *extra)
 	}
 }
 
-int commit_tree(const struct strbuf *msg, const unsigned char *tree,
+int commit_tree(const char *msg, size_t msg_len,
+		const unsigned char *tree,
 		struct commit_list *parents, unsigned char *ret,
 		const char *author, const char *sign_commit)
 {
@@ -1352,7 +1404,7 @@ int commit_tree(const struct strbuf *msg, const unsigned char *tree,
 	int result;
 
 	append_merge_tag_headers(parents, &tail);
-	result = commit_tree_extended(msg, tree, parents, ret,
+	result = commit_tree_extended(msg, msg_len, tree, parents, ret,
 				      author, sign_commit, extra);
 	free_commit_extra_headers(extra);
 	return result;
@@ -1473,7 +1525,8 @@ static const char commit_utf8_warn[] =
 "You may want to amend it after fixing the message, or set the config\n"
 "variable i18n.commitencoding to the encoding your project uses.\n";
 
-int commit_tree_extended(const struct strbuf *msg, const unsigned char *tree,
+int commit_tree_extended(const char *msg, size_t msg_len,
+			 const unsigned char *tree,
 			 struct commit_list *parents, unsigned char *ret,
 			 const char *author, const char *sign_commit,
 			 struct commit_extra_header *extra)
@@ -1484,7 +1537,7 @@ int commit_tree_extended(const struct strbuf *msg, const unsigned char *tree,
 
 	assert_sha1_type(tree, OBJ_TREE);
 
-	if (memchr(msg->buf, '\0', msg->len))
+	if (memchr(msg, '\0', msg_len))
 		return error("a NUL byte in commit log message not allowed.");
 
 	/* Not having i18n.commitencoding is the same as having utf-8 */
@@ -1523,7 +1576,7 @@ int commit_tree_extended(const struct strbuf *msg, const unsigned char *tree,
 	strbuf_addch(&buffer, '\n');
 
 	/* And add the comment */
-	strbuf_addbuf(&buffer, msg);
+	strbuf_add(&buffer, msg, msg_len);
 
 	/* And check the encoding */
 	if (encoding_is_utf8 && !verify_utf8(&buffer))
diff --git a/commit.h b/commit.h
index a9f177ba48..2e1492a6e4 100644
--- a/commit.h
+++ b/commit.h
@@ -20,7 +20,6 @@ struct commit {
 	unsigned long date;
 	struct commit_list *parents;
 	struct tree *tree;
-	char *buffer;
 };
 
 extern int save_commit_buffer;
@@ -51,6 +50,44 @@ int parse_commit_buffer(struct commit *item, const void *buffer, unsigned long s
 int parse_commit(struct commit *item);
 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, 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 *, 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 *, unsigned long *size);
+
+/*
+ * Tell the commit subsytem that we are done with a particular commit buffer.
+ * The commit and buffer should be the input and return value, respectively,
+ * from an earlier call to get_commit_buffer.  The buffer may or may not be
+ * freed by this call; callers should not access the memory afterwards.
+ */
+void unuse_commit_buffer(const struct commit *, const void *buffer);
+
+/*
+ * Free any cached object buffer associated with the commit.
+ */
+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 *, unsigned long *sizep);
+
 /* Find beginning and length of commit subject. */
 int find_commit_subject(const char *commit_buffer, const char **subject);
 
@@ -115,10 +152,9 @@ struct userformat_want {
 
 extern int has_non_ascii(const char *text);
 struct rev_info; /* in revision.h, it circularly uses enum cmit_fmt */
-extern char *logmsg_reencode(const struct commit *commit,
-			     char **commit_encoding,
-			     const char *output_encoding);
-extern void logmsg_free(char *msg, const struct commit *commit);
+extern const char *logmsg_reencode(const struct commit *commit,
+				   char **commit_encoding,
+				   const char *output_encoding);
 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);
@@ -261,11 +297,13 @@ struct commit_extra_header {
 extern void append_merge_tag_headers(struct commit_list *parents,
 				     struct commit_extra_header ***tail);
 
-extern int commit_tree(const struct strbuf *msg, const unsigned char *tree,
+extern int commit_tree(const char *msg, size_t msg_len,
+		       const unsigned char *tree,
 		       struct commit_list *parents, unsigned char *ret,
 		       const char *author, const char *sign_commit);
 
-extern int commit_tree_extended(const struct strbuf *msg, const unsigned char *tree,
+extern int commit_tree_extended(const char *msg, size_t msg_len,
+				const unsigned char *tree,
 				struct commit_list *parents, unsigned char *ret,
 				const char *author, const char *sign_commit,
 				struct commit_extra_header *);
@@ -287,7 +325,7 @@ struct merge_remote_desc {
  */
 struct commit *get_merge_parent(const char *name);
 
-extern int parse_signed_commit(const unsigned char *sha1,
+extern int parse_signed_commit(const struct commit *commit,
 			       struct strbuf *message, struct strbuf *signature);
 extern void print_commit_list(struct commit_list *list,
 			      const char *format_cur,
diff --git a/fsck.c b/fsck.c
index abed62bac7..a7233c8d0b 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, NULL);
+	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/log-tree.c b/log-tree.c
index cf2f86c866..10e68442b3 100644
--- a/log-tree.c
+++ b/log-tree.c
@@ -376,7 +376,7 @@ static void show_signature(struct rev_info *opt, struct commit *commit)
 	struct strbuf gpg_output = STRBUF_INIT;
 	int status;
 
-	if (parse_signed_commit(commit->object.sha1, &payload, &signature) <= 0)
+	if (parse_signed_commit(commit, &payload, &signature) <= 0)
 		goto out;
 
 	status = verify_signed_buffer(payload.buf, payload.len,
@@ -588,7 +588,7 @@ void show_log(struct rev_info *opt)
 		show_mergetag(opt, commit);
 	}
 
-	if (!commit->buffer)
+	if (!get_cached_commit_buffer(commit, NULL))
 		return;
 
 	if (opt->show_notes) {
diff --git a/merge-recursive.c b/merge-recursive.c
index cab16fafb5..d38a3b2eb5 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -40,7 +40,7 @@ static struct tree *shift_tree_object(struct tree *one, struct tree *two,
 
 static struct commit *make_virtual_commit(struct tree *tree, const char *comment)
 {
-	struct commit *commit = xcalloc(1, sizeof(struct commit));
+	struct commit *commit = alloc_commit_node();
 	struct merge_remote_desc *desc = xmalloc(sizeof(*desc));
 
 	desc->name = comment;
@@ -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, NULL);
+			int len = find_commit_subject(msg, &title);
 			if (len)
 				printf("%.*s\n", len, title);
+			unuse_commit_buffer(commit, msg);
 		}
 	}
 }
diff --git a/notes-cache.c b/notes-cache.c
index eabe4a0d9b..25b20aa21f 100644
--- a/notes-cache.c
+++ b/notes-cache.c
@@ -48,7 +48,6 @@ int notes_cache_write(struct notes_cache *c)
 {
 	unsigned char tree_sha1[20];
 	unsigned char commit_sha1[20];
-	struct strbuf msg = STRBUF_INIT;
 
 	if (!c || !c->tree.initialized || !c->tree.ref || !*c->tree.ref)
 		return -1;
@@ -57,9 +56,8 @@ int notes_cache_write(struct notes_cache *c)
 
 	if (write_notes_tree(&c->tree, tree_sha1))
 		return -1;
-	strbuf_attach(&msg, c->validity,
-		      strlen(c->validity), strlen(c->validity) + 1);
-	if (commit_tree(&msg, tree_sha1, NULL, commit_sha1, NULL, NULL) < 0)
+	if (commit_tree(c->validity, strlen(c->validity), tree_sha1, NULL,
+			commit_sha1, NULL, NULL) < 0)
 		return -1;
 	if (update_ref("update notes cache", c->tree.ref, commit_sha1, NULL,
 		       0, QUIET_ON_ERR) < 0)
diff --git a/notes-merge.c b/notes-merge.c
index 94a1a8ae46..fd5fae255d 100644
--- a/notes-merge.c
+++ b/notes-merge.c
@@ -644,7 +644,8 @@ int notes_merge(struct notes_merge_options *o,
 		struct commit_list *parents = NULL;
 		commit_list_insert(remote, &parents); /* LIFO order */
 		commit_list_insert(local, &parents);
-		create_notes_commit(local_tree, parents, &o->commit_msg,
+		create_notes_commit(local_tree, parents,
+				    o->commit_msg.buf, o->commit_msg.len,
 				    result_sha1);
 	}
 
@@ -671,8 +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");
-	struct strbuf sb_msg = STRBUF_INIT;
+	const char *buffer = get_commit_buffer(partial_commit, NULL);
+	const char *msg = strstr(buffer, "\n\n");
 	int baselen;
 
 	strbuf_addstr(&path, git_path(NOTES_MERGE_WORKTREE));
@@ -719,9 +720,9 @@ int notes_merge_commit(struct notes_merge_options *o,
 		strbuf_setlen(&path, baselen);
 	}
 
-	strbuf_attach(&sb_msg, msg, strlen(msg), strlen(msg) + 1);
-	create_notes_commit(partial_tree, partial_commit->parents, &sb_msg,
-			    result_sha1);
+	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/notes-utils.c b/notes-utils.c
index 4aa7023903..f6891f7255 100644
--- a/notes-utils.c
+++ b/notes-utils.c
@@ -4,7 +4,8 @@
 #include "notes-utils.h"
 
 void create_notes_commit(struct notes_tree *t, struct commit_list *parents,
-			 const struct strbuf *msg, unsigned char *result_sha1)
+			 const char *msg, size_t msg_len,
+			 unsigned char *result_sha1)
 {
 	unsigned char tree_sha1[20];
 
@@ -25,7 +26,7 @@ void create_notes_commit(struct notes_tree *t, struct commit_list *parents,
 		/* else: t->ref points to nothing, assume root/orphan commit */
 	}
 
-	if (commit_tree(msg, tree_sha1, parents, result_sha1, NULL, NULL))
+	if (commit_tree(msg, msg_len, tree_sha1, parents, result_sha1, NULL, NULL))
 		die("Failed to commit notes tree to database");
 }
 
@@ -46,7 +47,7 @@ void commit_notes(struct notes_tree *t, const char *msg)
 	if (buf.buf[buf.len - 1] != '\n')
 		strbuf_addch(&buf, '\n'); /* Make sure msg ends with newline */
 
-	create_notes_commit(t, NULL, &buf, commit_sha1);
+	create_notes_commit(t, NULL, buf.buf, buf.len, commit_sha1);
 	strbuf_insert(&buf, 0, "notes: ", 7); /* commit message starts at index 7 */
 	update_ref(buf.buf, t->ref, commit_sha1, NULL, 0, DIE_ON_ERR);
 
diff --git a/notes-utils.h b/notes-utils.h
index 564e30cccd..890ddb33e1 100644
--- a/notes-utils.h
+++ b/notes-utils.h
@@ -15,7 +15,7 @@
  * The resulting commit SHA1 is stored in result_sha1.
  */
 void create_notes_commit(struct notes_tree *t, struct commit_list *parents,
-			 const struct strbuf *msg, unsigned char *result_sha1);
+			 const char *msg, size_t msg_len, unsigned char *result_sha1);
 
 void commit_notes(struct notes_tree *t, const char *msg);
 
diff --git a/object.c b/object.c
index 57a0890a87..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 (!commit->buffer) {
-				commit->buffer = 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 5c02b29ceb..32099632f6 100644
--- a/pretty.c
+++ b/pretty.c
@@ -606,29 +606,16 @@ static char *replace_encoding_header(char *buf, const char *encoding)
 	return strbuf_detach(&tmp, NULL);
 }
 
-char *logmsg_reencode(const struct commit *commit,
-		      char **commit_encoding,
-		      const char *output_encoding)
+const char *logmsg_reencode(const struct commit *commit,
+			    char **commit_encoding,
+			    const char *output_encoding)
 {
 	static const char *utf8 = "UTF-8";
 	const char *use_encoding;
 	char *encoding;
-	char *msg = commit->buffer;
+	const char *msg = get_commit_buffer(commit, NULL);
 	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 @@ 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, NULL))
+			out = xstrdup(msg);
+		else
+			out = (char *)msg;
 	}
 	else {
 		/*
@@ -667,8 +655,8 @@ 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 @@ char *logmsg_reencode(const struct commit *commit,
 	return out ? out : msg;
 }
 
-void logmsg_free(char *msg, const struct commit *commit)
-{
-	if (msg != commit->buffer)
-		free(msg);
-}
-
 static int mailmap_name(const char **email, size_t *email_len,
 			const char **name, size_t *name_len)
 {
@@ -796,7 +778,7 @@ struct format_commit_context {
 	struct signature_check signature_check;
 	enum flush_type flush_type;
 	enum trunc_type truncate;
-	char *message;
+	const char *message;
 	char *commit_encoding;
 	size_t width, indent1, indent2;
 	int auto_color;
@@ -1536,7 +1518,7 @@ 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);
 }
@@ -1705,7 +1687,7 @@ void pretty_print_commit(struct pretty_print_context *pp,
 	unsigned long beginning_of_body;
 	int indent = 4;
 	const char *msg;
-	char *reencoded;
+	const char *reencoded;
 	const char *encoding;
 	int need_8bit_cte = pp->need_8bit_cte;
 
@@ -1772,7 +1754,7 @@ 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 8351e794df..2571ada6bf 100644
--- a/revision.c
+++ b/revision.c
@@ -2791,7 +2791,7 @@ static int commit_match(struct commit *commit, struct rev_info *opt)
 {
 	int retval;
 	const char *encoding;
-	char *message;
+	const char *message;
 	struct strbuf buf = STRBUF_INIT;
 
 	if (!opt->grep_filter.pattern_list && !opt->grep_filter.header_list)
@@ -2833,14 +2833,21 @@ static int commit_match(struct commit *commit, struct rev_info *opt)
 		format_display_notes(commit->object.sha1, &buf, encoding, 1);
 	}
 
-	/* Find either in the original commit message, or in the temporary */
+	/*
+	 * Find either in the original commit message, or in the temporary.
+	 * Note that we cast away the constness of "message" here. It is
+	 * const because it may come from the cached commit buffer. That's OK,
+	 * because we know that it is modifiable heap memory, and that while
+	 * grep_buffer may modify it for speed, it will restore any
+	 * changes before returning.
+	 */
 	if (buf.len)
 		retval = grep_buffer(&opt->grep_filter, buf.buf, buf.len);
 	else
 		retval = grep_buffer(&opt->grep_filter,
-				     message, strlen(message));
+				     (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 bde5f047b0..bbaddcb05a 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;
+	unuse_commit_buffer(commit, msg->message);
 }
 
 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;
@@ -697,10 +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, NULL);
 		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;
 }
diff --git a/sha1_name.c b/sha1_name.c
index 2b6322fad0..c2c938c4e1 100644
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -862,27 +862,17 @@ static int get_sha1_oneline(const char *prefix, unsigned char *sha1,
 		commit_list_insert(l->item, &backup);
 	}
 	while (list) {
-		char *p, *to_free = NULL;
+		const char *p, *buf;
 		struct commit *commit;
-		enum object_type type;
-		unsigned long size;
 		int matches;
 
 		commit = pop_most_recent_commit(&list, ONELINE_SEEN);
 		if (!parse_object(commit->object.sha1))
 			continue;
-		if (commit->buffer)
-			p = commit->buffer;
-		else {
-			p = read_sha1_file(commit->object.sha1, &type, &size);
-			if (!p)
-				continue;
-			to_free = p;
-		}
-
-		p = strstr(p, "\n\n");
+		buf = get_commit_buffer(commit, NULL);
+		p = strstr(buf, "\n\n");
 		matches = p && !regexec(&regex, p + 2, 0, NULL, 0);
-		free(to_free);
+		unuse_commit_buffer(commit, buf);
 
 		if (matches) {
 			hashcpy(sha1, commit->object.sha1);