From: Junio C Hamano <gitster@pobox.com>
Date: Fri, 12 Aug 2016 16:47:39 +0000 (-0700)
Subject: Merge branch 'kw/patch-ids-optim'
X-Git-Tag: v2.10.0-rc0~3
X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/dd610aeda684e42d3933a719cbd59ffbcdfdbcaa?ds=inline;hp=-c

Merge branch 'kw/patch-ids-optim'

When "git rebase" tries to compare set of changes on the updated
upstream and our own branch, it computes patch-id for all of these
changes and attempts to find matches. This has been optimized by
lazily computing the full patch-id (which is expensive) to be
compared only for changes that touch the same set of paths.

* kw/patch-ids-optim:
rebase: avoid computing unnecessary patch IDs
patch-ids: add flag to create the diff patch id using header only data
patch-ids: replace the seen indicator with a commit pointer
patch-ids: stop using a hand-rolled hashmap implementation
---

dd610aeda684e42d3933a719cbd59ffbcdfdbcaa
diff --combined builtin/log.c
index 1f116bea8c,e36457288a..92dc34dcb0
--- a/builtin/log.c
+++ b/builtin/log.c
@@@ -33,7 -33,6 +33,7 @@@ static const char *default_date_mode = 
  static int default_abbrev_commit;
  static int default_show_root = 1;
  static int default_follow;
 +static int default_show_signature;
  static int decoration_style;
  static int decoration_given;
  static int use_mailmap_config;
@@@ -120,7 -119,6 +120,7 @@@ static void cmd_log_init_defaults(struc
  	rev->abbrev_commit = default_abbrev_commit;
  	rev->show_root_diff = default_show_root;
  	rev->subject_prefix = fmt_patch_subject_prefix;
 +	rev->show_signature = default_show_signature;
  	DIFF_OPT_SET(&rev->diffopt, ALLOW_TEXTCONV);
  
  	if (default_date_mode)
@@@ -238,17 -236,16 +238,17 @@@ static void show_early_header(struct re
  		if (rev->commit_format != CMIT_FMT_ONELINE)
  			putchar(rev->diffopt.line_termination);
  	}
 -	printf(_("Final output: %d %s\n"), nr, stage);
 +	fprintf(rev->diffopt.file, _("Final output: %d %s\n"), nr, stage);
  }
  
  static struct itimerval early_output_timer;
  
  static void log_show_early(struct rev_info *revs, struct commit_list *list)
  {
 -	int i = revs->early_output;
 +	int i = revs->early_output, close_file = revs->diffopt.close_file;
  	int show_header = 1;
  
 +	revs->diffopt.close_file = 0;
  	sort_in_topological_order(&list, revs->sort_order);
  	while (list && i) {
  		struct commit *commit = list->item;
@@@ -265,19 -262,14 +265,19 @@@
  		case commit_ignore:
  			break;
  		case commit_error:
 +			if (close_file)
 +				fclose(revs->diffopt.file);
  			return;
  		}
  		list = list->next;
  	}
  
  	/* Did we already get enough commits for the early output? */
 -	if (!i)
 +	if (!i) {
 +		if (close_file)
 +			fclose(revs->diffopt.file);
  		return;
 +	}
  
  	/*
  	 * ..if no, then repeat it twice a second until we
@@@ -339,7 -331,7 +339,7 @@@ static int cmd_log_walk(struct rev_inf
  {
  	struct commit *commit;
  	int saved_nrl = 0;
 -	int saved_dcctc = 0;
 +	int saved_dcctc = 0, close_file = rev->diffopt.close_file;
  
  	if (rev->early_output)
  		setup_early_output(rev);
@@@ -355,7 -347,6 +355,7 @@@
  	 * and HAS_CHANGES being accumulated in rev->diffopt, so be careful to
  	 * retain that state information if replacing rev->diffopt in this loop
  	 */
 +	rev->diffopt.close_file = 0;
  	while ((commit = get_revision(rev)) != NULL) {
  		if (!log_tree_commit(rev, commit) && rev->max_count >= 0)
  			/*
@@@ -376,8 -367,6 +376,8 @@@
  	}
  	rev->diffopt.degraded_cc_to_c = saved_dcctc;
  	rev->diffopt.needed_rename_limit = saved_nrl;
 +	if (close_file)
 +		fclose(rev->diffopt.file);
  
  	if (rev->diffopt.output_format & DIFF_FORMAT_CHECKDIFF &&
  	    DIFF_OPT_TST(&rev->diffopt, CHECK_FAILED)) {
@@@ -420,10 -409,6 +420,10 @@@ static int git_log_config(const char *v
  		use_mailmap_config = git_config_bool(var, value);
  		return 0;
  	}
 +	if (!strcmp(var, "log.showsignature")) {
 +		default_show_signature = git_config_bool(var, value);
 +		return 0;
 +	}
  
  	if (grep_config(var, value, cb) < 0)
  		return -1;
@@@ -460,7 -445,7 +460,7 @@@ static void show_tagger(char *buf, int 
  	pp.fmt = rev->commit_format;
  	pp.date_mode = rev->date_mode;
  	pp_user_info(&pp, "Tagger", &out, buf, get_log_output_encoding());
 -	printf("%s", out.buf);
 +	fprintf(rev->diffopt.file, "%s", out.buf);
  	strbuf_release(&out);
  }
  
@@@ -471,7 -456,7 +471,7 @@@ static int show_blob_object(const unsig
  	char *buf;
  	unsigned long size;
  
 -	fflush(stdout);
 +	fflush(rev->diffopt.file);
  	if (!DIFF_OPT_TOUCHED(&rev->diffopt, ALLOW_TEXTCONV) ||
  	    !DIFF_OPT_TST(&rev->diffopt, ALLOW_TEXTCONV))
  		return stream_blob_to_fd(1, sha1, NULL, 0);
@@@ -511,7 -496,7 +511,7 @@@ static int show_tag_object(const unsign
  	}
  
  	if (offset < size)
 -		fwrite(buf + offset, size - offset, 1, stdout);
 +		fwrite(buf + offset, size - offset, 1, rev->diffopt.file);
  	free(buf);
  	return 0;
  }
@@@ -520,8 -505,7 +520,8 @@@ static int show_tree_object(const unsig
  		struct strbuf *base,
  		const char *pathname, unsigned mode, int stage, void *context)
  {
 -	printf("%s%s\n", pathname, S_ISDIR(mode) ? "/" : "");
 +	FILE *file = context;
 +	fprintf(file, "%s%s\n", pathname, S_ISDIR(mode) ? "/" : "");
  	return 0;
  }
  
@@@ -581,7 -565,7 +581,7 @@@ int cmd_show(int argc, const char **arg
  
  			if (rev.shown_one)
  				putchar('\n');
 -			printf("%stag %s%s\n",
 +			fprintf(rev.diffopt.file, "%stag %s%s\n",
  					diff_get_color_opt(&rev.diffopt, DIFF_COMMIT),
  					t->tag,
  					diff_get_color_opt(&rev.diffopt, DIFF_RESET));
@@@ -600,12 -584,12 +600,12 @@@
  		case OBJ_TREE:
  			if (rev.shown_one)
  				putchar('\n');
 -			printf("%stree %s%s\n\n",
 +			fprintf(rev.diffopt.file, "%stree %s%s\n\n",
  					diff_get_color_opt(&rev.diffopt, DIFF_COMMIT),
  					name,
  					diff_get_color_opt(&rev.diffopt, DIFF_RESET));
  			read_tree_recursive((struct tree *)o, "", 0, 0, &match_all,
 -					show_tree_object, NULL);
 +					show_tree_object, rev.diffopt.file);
  			rev.shown_one = 1;
  			break;
  		case OBJ_COMMIT:
@@@ -690,9 -674,9 +690,9 @@@ static int auto_number = 1
  
  static char *default_attach = NULL;
  
 -static struct string_list extra_hdr;
 -static struct string_list extra_to;
 -static struct string_list extra_cc;
 +static struct string_list extra_hdr = STRING_LIST_INIT_NODUP;
 +static struct string_list extra_to = STRING_LIST_INIT_NODUP;
 +static struct string_list extra_cc = STRING_LIST_INIT_NODUP;
  
  static void add_header(const char *value)
  {
@@@ -719,7 -703,6 +719,7 @@@
  static int thread;
  static int do_signoff;
  static int base_auto;
 +static char *from;
  static const char *signature = git_version_string;
  static const char *signature_file;
  static int config_cover_letter;
@@@ -808,25 -791,15 +808,25 @@@ static int git_format_config(const cha
  		base_auto = git_config_bool(var, value);
  		return 0;
  	}
 +	if (!strcmp(var, "format.from")) {
 +		int b = git_config_maybe_bool(var, value);
 +		free(from);
 +		if (b < 0)
 +			from = xstrdup(value);
 +		else if (b)
 +			from = xstrdup(git_committer_info(IDENT_NO_DATE));
 +		else
 +			from = NULL;
 +		return 0;
 +	}
  
  	return git_log_config(var, value, cb);
  }
  
 -static FILE *realstdout = NULL;
  static const char *output_directory = NULL;
  static int outdir_offset;
  
 -static int reopen_stdout(struct commit *commit, const char *subject,
 +static int open_next_file(struct commit *commit, const char *subject,
  			 struct rev_info *rev, int quiet)
  {
  	struct strbuf filename = STRBUF_INIT;
@@@ -848,9 -821,9 +848,9 @@@
  		fmt_output_subject(&filename, subject, rev);
  
  	if (!quiet)
 -		fprintf(realstdout, "%s\n", filename.buf + outdir_offset);
 +		printf("%s\n", filename.buf + outdir_offset);
  
 -	if (freopen(filename.buf, "w", stdout) == NULL)
 +	if ((rev->diffopt.file = fopen(filename.buf, "w")) == NULL)
  		return error(_("Cannot open patch file %s"), filename.buf);
  
  	strbuf_release(&filename);
@@@ -909,15 -882,15 +909,15 @@@ static void gen_message_id(struct rev_i
  	info->message_id = strbuf_detach(&buf, NULL);
  }
  
 -static void print_signature(void)
 +static void print_signature(FILE *file)
  {
  	if (!signature || !*signature)
  		return;
  
 -	printf("-- \n%s", signature);
 +	fprintf(file, "-- \n%s", signature);
  	if (signature[strlen(signature)-1] != '\n')
 -		putchar('\n');
 -	putchar('\n');
 +		putc('\n', file);
 +	putc('\n', file);
  }
  
  static void add_branch_description(struct strbuf *buf, const char *branch_name)
@@@ -980,13 -953,13 +980,13 @@@ static void make_cover_letter(struct re
  	struct pretty_print_context pp = {0};
  	struct commit *head = list[0];
  
 -	if (rev->commit_format != CMIT_FMT_EMAIL)
 +	if (!cmit_fmt_is_mail(rev->commit_format))
  		die(_("Cover letter needs email format"));
  
  	committer = git_committer_info(0);
  
  	if (!use_stdout &&
 -	    reopen_stdout(NULL, rev->numbered_files ? NULL : "cover-letter", rev, quiet))
 +	    open_next_file(NULL, rev->numbered_files ? NULL : "cover-letter", rev, quiet))
  		return;
  
  	log_write_email_headers(rev, head, &pp.subject, &pp.after_subject,
@@@ -1009,7 -982,7 +1009,7 @@@
  	pp_title_line(&pp, &msg, &sb, encoding, need_8bit_cte);
  	pp_remainder(&pp, &msg, &sb, 0);
  	add_branch_description(&sb, branch_name);
 -	printf("%s\n", sb.buf);
 +	fprintf(rev->diffopt.file, "%s\n", sb.buf);
  
  	strbuf_release(&sb);
  
@@@ -1018,7 -991,6 +1018,7 @@@
  	log.wrap = 72;
  	log.in1 = 2;
  	log.in2 = 4;
 +	log.file = rev->diffopt.file;
  	for (i = 0; i < nr; i++)
  		shortlog_add_commit(&log, list[i]);
  
@@@ -1041,8 -1013,8 +1041,8 @@@
  	diffcore_std(&opts);
  	diff_flush(&opts);
  
 -	printf("\n");
 -	print_signature();
 +	fprintf(rev->diffopt.file, "\n");
 +	print_signature(rev->diffopt.file);
  }
  
  static const char *clean_message_id(const char *msg_id)
@@@ -1343,7 -1315,7 +1343,7 @@@ static void prepare_bases(struct base_t
  		struct object_id *patch_id;
  		if (commit->util)
  			continue;
- 		if (commit_patch_id(commit, &diffopt, sha1))
+ 		if (commit_patch_id(commit, &diffopt, sha1, 0))
  			die(_("cannot get patch id"));
  		ALLOC_GROW(bases->patch_id, bases->nr_patch_id + 1, bases->alloc_patch_id);
  		patch_id = bases->patch_id + bases->nr_patch_id;
@@@ -1352,7 -1324,7 +1352,7 @@@
  	}
  }
  
 -static void print_bases(struct base_tree_info *bases)
 +static void print_bases(struct base_tree_info *bases, FILE *file)
  {
  	int i;
  
@@@ -1361,11 -1333,11 +1361,11 @@@
  		return;
  
  	/* Show the base commit */
 -	printf("base-commit: %s\n", oid_to_hex(&bases->base_commit));
 +	fprintf(file, "base-commit: %s\n", oid_to_hex(&bases->base_commit));
  
  	/* Show the prerequisite patches */
  	for (i = bases->nr_patch_id - 1; i >= 0; i--)
 -		printf("prerequisite-patch-id: %s\n", oid_to_hex(&bases->patch_id[i]));
 +		fprintf(file, "prerequisite-patch-id: %s\n", oid_to_hex(&bases->patch_id[i]));
  
  	free(bases->patch_id);
  	bases->nr_patch_id = 0;
@@@ -1396,6 -1368,7 +1396,6 @@@ int cmd_format_patch(int argc, const ch
  	int quiet = 0;
  	int reroll_count = -1;
  	char *branch_name = NULL;
 -	char *from = NULL;
  	char *base_commit = NULL;
  	struct base_tree_info bases;
  
@@@ -1596,8 -1569,6 +1596,8 @@@
  		setup_pager();
  
  	if (output_directory) {
 +		if (rev.diffopt.use_color != GIT_COLOR_ALWAYS)
 +			rev.diffopt.use_color = GIT_COLOR_NEVER;
  		if (use_stdout)
  			die(_("standard output, or directory, which one?"));
  		if (mkdir(output_directory, 0777) < 0 && errno != EEXIST)
@@@ -1655,6 -1626,9 +1655,6 @@@
  		get_patch_ids(&rev, &ids);
  	}
  
 -	if (!use_stdout)
 -		realstdout = xfdopen(xdup(1), "w");
 -
  	if (prepare_revision_walk(&rev))
  		die(_("revision walk setup failed"));
  	rev.boundary = 1;
@@@ -1719,7 -1693,7 +1719,7 @@@
  			gen_message_id(&rev, "cover");
  		make_cover_letter(&rev, use_stdout,
  				  origin, nr, list, branch_name, quiet);
 -		print_bases(&bases);
 +		print_bases(&bases, rev.diffopt.file);
  		total++;
  		start_number--;
  	}
@@@ -1765,7 -1739,7 +1765,7 @@@
  		}
  
  		if (!use_stdout &&
 -		    reopen_stdout(rev.numbered_files ? NULL : commit, NULL, &rev, quiet))
 +		    open_next_file(rev.numbered_files ? NULL : commit, NULL, &rev, quiet))
  			die(_("Failed to create output files"));
  		shown = log_tree_commit(&rev, commit);
  		free_commit_buffer(commit);
@@@ -1780,15 -1754,15 +1780,15 @@@
  			rev.shown_one = 0;
  		if (shown) {
  			if (rev.mime_boundary)
 -				printf("\n--%s%s--\n\n\n",
 +				fprintf(rev.diffopt.file, "\n--%s%s--\n\n\n",
  				       mime_boundary_leader,
  				       rev.mime_boundary);
  			else
 -				print_signature();
 -			print_bases(&bases);
 +				print_signature(rev.diffopt.file);
 +			print_bases(&bases, rev.diffopt.file);
  		}
  		if (!use_stdout)
 -			fclose(stdout);
 +			fclose(rev.diffopt.file);
  	}
  	free(list);
  	free(branch_name);
@@@ -1820,15 -1794,15 +1820,15 @@@ static const char * const cherry_usage[
  };
  
  static void print_commit(char sign, struct commit *commit, int verbose,
 -			 int abbrev)
 +			 int abbrev, FILE *file)
  {
  	if (!verbose) {
 -		printf("%c %s\n", sign,
 +		fprintf(file, "%c %s\n", sign,
  		       find_unique_abbrev(commit->object.oid.hash, abbrev));
  	} else {
  		struct strbuf buf = STRBUF_INIT;
  		pp_commit_easy(CMIT_FMT_ONELINE, commit, &buf);
 -		printf("%c %s %s\n", sign,
 +		fprintf(file, "%c %s %s\n", sign,
  		       find_unique_abbrev(commit->object.oid.hash, abbrev),
  		       buf.buf);
  		strbuf_release(&buf);
@@@ -1909,7 -1883,7 +1909,7 @@@ int cmd_cherry(int argc, const char **a
  		commit = list->item;
  		if (has_commit_patch_id(commit, &ids))
  			sign = '-';
 -		print_commit(sign, commit, verbose, abbrev);
 +		print_commit(sign, commit, verbose, abbrev, revs.diffopt.file);
  		list = list->next;
  	}
  
diff --combined diff.c
index b43d3dd2ec,bb816d9cba..534c12e28e
--- a/diff.c
+++ b/diff.c
@@@ -1933,8 -1933,8 +1933,8 @@@ static void show_dirstat(struct diff_op
  
  		name = p->two->path ? p->two->path : p->one->path;
  
 -		if (p->one->sha1_valid && p->two->sha1_valid)
 -			content_changed = hashcmp(p->one->sha1, p->two->sha1);
 +		if (p->one->oid_valid && p->two->oid_valid)
 +			content_changed = oidcmp(&p->one->oid, &p->two->oid);
  		else
  			content_changed = 1;
  
@@@ -2306,8 -2306,7 +2306,8 @@@ static void builtin_diff(const char *na
  		const char *add = diff_get_color_opt(o, DIFF_FILE_NEW);
  		show_submodule_summary(o->file, one->path ? one->path : two->path,
  				line_prefix,
 -				one->sha1, two->sha1, two->dirty_submodule,
 +				one->oid.hash, two->oid.hash,
 +				two->dirty_submodule,
  				meta, del, add, reset);
  		return;
  	}
@@@ -2385,7 -2384,7 +2385,7 @@@
  		if (!one->data && !two->data &&
  		    S_ISREG(one->mode) && S_ISREG(two->mode) &&
  		    !DIFF_OPT_TST(o, BINARY)) {
 -			if (!hashcmp(one->sha1, two->sha1)) {
 +			if (!oidcmp(&one->oid, &two->oid)) {
  				if (must_show_header)
  					fprintf(o->file, "%s", header.buf);
  				goto free_ab_and_return;
@@@ -2506,7 -2505,7 +2506,7 @@@ static void builtin_diffstat(const cha
  		return;
  	}
  
 -	same_contents = !hashcmp(one->sha1, two->sha1);
 +	same_contents = !oidcmp(&one->oid, &two->oid);
  
  	if (diff_filespec_is_binary(one) || diff_filespec_is_binary(two)) {
  		data->is_binary = 1;
@@@ -2639,8 -2638,8 +2639,8 @@@ void fill_filespec(struct diff_filespe
  {
  	if (mode) {
  		spec->mode = canon_mode(mode);
 -		hashcpy(spec->sha1, sha1);
 -		spec->sha1_valid = sha1_valid;
 +		hashcpy(spec->oid.hash, sha1);
 +		spec->oid_valid = sha1_valid;
  	}
  }
  
@@@ -2683,13 -2682,6 +2683,13 @@@ static int reuse_worktree_file(const ch
  	if (!FAST_WORKING_DIRECTORY && !want_file && has_sha1_pack(sha1))
  		return 0;
  
 +	/*
 +	 * Similarly, if we'd have to convert the file contents anyway, that
 +	 * makes the optimization not worthwhile.
 +	 */
 +	if (!want_file && would_convert_to_git(name))
 +		return 0;
 +
  	len = strlen(name);
  	pos = cache_name_pos(name, len);
  	if (pos < 0)
@@@ -2729,8 -2721,7 +2729,8 @@@ static int diff_populate_gitlink(struc
  	if (s->dirty_submodule)
  		dirty = "-dirty";
  
 -	strbuf_addf(&buf, "Subproject commit %s%s\n", sha1_to_hex(s->sha1), dirty);
 +	strbuf_addf(&buf, "Subproject commit %s%s\n",
 +		    oid_to_hex(&s->oid), dirty);
  	s->size = buf.len;
  	if (size_only) {
  		s->data = NULL;
@@@ -2773,8 -2764,8 +2773,8 @@@ int diff_populate_filespec(struct diff_
  	if (S_ISGITLINK(s->mode))
  		return diff_populate_gitlink(s, size_only);
  
 -	if (!s->sha1_valid ||
 -	    reuse_worktree_file(s->path, s->sha1, 0)) {
 +	if (!s->oid_valid ||
 +	    reuse_worktree_file(s->path, s->oid.hash, 0)) {
  		struct strbuf buf = STRBUF_INIT;
  		struct stat st;
  		int fd;
@@@ -2831,10 -2822,9 +2831,10 @@@
  	else {
  		enum object_type type;
  		if (size_only || (flags & CHECK_BINARY)) {
 -			type = sha1_object_info(s->sha1, &s->size);
 +			type = sha1_object_info(s->oid.hash, &s->size);
  			if (type < 0)
 -				die("unable to read %s", sha1_to_hex(s->sha1));
 +				die("unable to read %s",
 +				    oid_to_hex(&s->oid));
  			if (size_only)
  				return 0;
  			if (s->size > big_file_threshold && s->is_binary == -1) {
@@@ -2842,9 -2832,9 +2842,9 @@@
  				return 0;
  			}
  		}
 -		s->data = read_sha1_file(s->sha1, &type, &s->size);
 +		s->data = read_sha1_file(s->oid.hash, &type, &s->size);
  		if (!s->data)
 -			die("unable to read %s", sha1_to_hex(s->sha1));
 +			die("unable to read %s", oid_to_hex(&s->oid));
  		s->should_free = 1;
  	}
  	return 0;
@@@ -2873,7 -2863,7 +2873,7 @@@ void diff_free_filespec_data(struct dif
  static void prep_temp_blob(const char *path, struct diff_tempfile *temp,
  			   void *blob,
  			   unsigned long size,
 -			   const unsigned char *sha1,
 +			   const struct object_id *oid,
  			   int mode)
  {
  	int fd;
@@@ -2898,7 -2888,7 +2898,7 @@@
  		die_errno("unable to write temp-file");
  	close_tempfile(&temp->tempfile);
  	temp->name = get_tempfile_path(&temp->tempfile);
 -	sha1_to_hex_r(temp->hex, sha1);
 +	oid_to_hex_r(temp->hex, oid);
  	xsnprintf(temp->mode, sizeof(temp->mode), "%06o", mode);
  	strbuf_release(&buf);
  	strbuf_release(&template);
@@@ -2922,8 -2912,8 +2922,8 @@@ static struct diff_tempfile *prepare_te
  	}
  
  	if (!S_ISGITLINK(one->mode) &&
 -	    (!one->sha1_valid ||
 -	     reuse_worktree_file(name, one->sha1, 1))) {
 +	    (!one->oid_valid ||
 +	     reuse_worktree_file(name, one->oid.hash, 1))) {
  		struct stat st;
  		if (lstat(name, &st) < 0) {
  			if (errno == ENOENT)
@@@ -2935,19 -2925,19 +2935,19 @@@
  			if (strbuf_readlink(&sb, name, st.st_size) < 0)
  				die_errno("readlink(%s)", name);
  			prep_temp_blob(name, temp, sb.buf, sb.len,
 -				       (one->sha1_valid ?
 -					one->sha1 : null_sha1),
 -				       (one->sha1_valid ?
 +				       (one->oid_valid ?
 +					&one->oid : &null_oid),
 +				       (one->oid_valid ?
  					one->mode : S_IFLNK));
  			strbuf_release(&sb);
  		}
  		else {
  			/* we can borrow from the file in the work tree */
  			temp->name = name;
 -			if (!one->sha1_valid)
 +			if (!one->oid_valid)
  				sha1_to_hex_r(temp->hex, null_sha1);
  			else
 -				sha1_to_hex_r(temp->hex, one->sha1);
 +				sha1_to_hex_r(temp->hex, one->oid.hash);
  			/* Even though we may sometimes borrow the
  			 * contents from the work tree, we always want
  			 * one->mode.  mode is trustworthy even when
@@@ -2962,7 -2952,7 +2962,7 @@@
  		if (diff_populate_filespec(one, 0))
  			die("cannot read data blob for %s", one->path);
  		prep_temp_blob(name, temp, one->data, one->size,
 -			       one->sha1, one->mode);
 +			       &one->oid, one->mode);
  	}
  	return temp;
  }
@@@ -3075,7 -3065,7 +3075,7 @@@ static void fill_metainfo(struct strbu
  	default:
  		*must_show_header = 0;
  	}
 -	if (one && two && hashcmp(one->sha1, two->sha1)) {
 +	if (one && two && oidcmp(&one->oid, &two->oid)) {
  		int abbrev = DIFF_OPT_TST(o, FULL_INDEX) ? 40 : DEFAULT_ABBREV;
  
  		if (DIFF_OPT_TST(o, BINARY)) {
@@@ -3085,8 -3075,8 +3085,8 @@@
  				abbrev = 40;
  		}
  		strbuf_addf(msg, "%s%sindex %s..", line_prefix, set,
 -			    find_unique_abbrev(one->sha1, abbrev));
 -		strbuf_addstr(msg, find_unique_abbrev(two->sha1, abbrev));
 +			    find_unique_abbrev(one->oid.hash, abbrev));
 +		strbuf_addstr(msg, find_unique_abbrev(two->oid.hash, abbrev));
  		if (one->mode == two->mode)
  			strbuf_addf(msg, " %06o", one->mode);
  		strbuf_addf(msg, "%s\n", reset);
@@@ -3141,20 -3131,20 +3141,20 @@@ static void run_diff_cmd(const char *pg
  static void diff_fill_sha1_info(struct diff_filespec *one)
  {
  	if (DIFF_FILE_VALID(one)) {
 -		if (!one->sha1_valid) {
 +		if (!one->oid_valid) {
  			struct stat st;
  			if (one->is_stdin) {
 -				hashcpy(one->sha1, null_sha1);
 +				oidclr(&one->oid);
  				return;
  			}
  			if (lstat(one->path, &st) < 0)
  				die_errno("stat '%s'", one->path);
 -			if (index_path(one->sha1, one->path, &st, 0))
 +			if (index_path(one->oid.hash, one->path, &st, 0))
  				die("cannot hash %s", one->path);
  		}
  	}
  	else
 -		hashclr(one->sha1);
 +		oidclr(&one->oid);
  }
  
  static void strip_prefix(int prefix_length, const char **namep, const char **otherp)
@@@ -3987,8 -3977,6 +3987,8 @@@ int diff_opt_parse(struct diff_options 
  		if (!options->file)
  			die_errno("Could not open '%s'", path);
  		options->close_file = 1;
 +		if (options->use_color != GIT_COLOR_ALWAYS)
 +			options->use_color = GIT_COLOR_NEVER;
  		return argcount;
  	} else
  		return 0;
@@@ -4130,9 -4118,8 +4130,9 @@@ static void diff_flush_raw(struct diff_
  	fprintf(opt->file, "%s", diff_line_prefix(opt));
  	if (!(opt->output_format & DIFF_FORMAT_NAME_STATUS)) {
  		fprintf(opt->file, ":%06o %06o %s ", p->one->mode, p->two->mode,
 -			diff_unique_abbrev(p->one->sha1, opt->abbrev));
 -		fprintf(opt->file, "%s ", diff_unique_abbrev(p->two->sha1, opt->abbrev));
 +			diff_unique_abbrev(p->one->oid.hash, opt->abbrev));
 +		fprintf(opt->file, "%s ",
 +			diff_unique_abbrev(p->two->oid.hash, opt->abbrev));
  	}
  	if (p->score) {
  		fprintf(opt->file, "%c%03d%c", p->status, similarity_index(p),
@@@ -4181,11 -4168,11 +4181,11 @@@ int diff_unmodified_pair(struct diff_fi
  	/* both are valid and point at the same path.  that is, we are
  	 * dealing with a change.
  	 */
 -	if (one->sha1_valid && two->sha1_valid &&
 -	    !hashcmp(one->sha1, two->sha1) &&
 +	if (one->oid_valid && two->oid_valid &&
 +	    !oidcmp(&one->oid, &two->oid) &&
  	    !one->dirty_submodule && !two->dirty_submodule)
  		return 1; /* no change */
 -	if (!one->sha1_valid && !two->sha1_valid)
 +	if (!one->oid_valid && !two->oid_valid)
  		return 1; /* both look at the same file on the filesystem. */
  	return 0;
  }
@@@ -4246,7 -4233,7 +4246,7 @@@ void diff_debug_filespec(struct diff_fi
  		s->path,
  		DIFF_FILE_VALID(s) ? "valid" : "invalid",
  		s->mode,
 -		s->sha1_valid ? sha1_to_hex(s->sha1) : "");
 +		s->oid_valid ? oid_to_hex(&s->oid) : "");
  	fprintf(stderr, "queue[%d] %s size %lu\n",
  		x, one ? one : "",
  		s->size);
@@@ -4316,11 -4303,11 +4316,11 @@@ static void diff_resolve_rename_copy(vo
  			else
  				p->status = DIFF_STATUS_RENAMED;
  		}
 -		else if (hashcmp(p->one->sha1, p->two->sha1) ||
 +		else if (oidcmp(&p->one->oid, &p->two->oid) ||
  			 p->one->mode != p->two->mode ||
  			 p->one->dirty_submodule ||
  			 p->two->dirty_submodule ||
 -			 is_null_sha1(p->one->sha1))
 +			 is_null_oid(&p->one->oid))
  			p->status = DIFF_STATUS_MODIFIED;
  		else {
  			/* This is a "no-change" entry and should not
@@@ -4462,7 -4449,7 +4462,7 @@@ static void patch_id_consume(void *priv
  }
  
  /* returns 0 upon success, and writes result into sha1 */
- static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
+ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1, int diff_header_only)
  {
  	struct diff_queue_struct *q = &diff_queued_diff;
  	int i;
@@@ -4497,9 -4484,6 +4497,6 @@@
  
  		diff_fill_sha1_info(p->one);
  		diff_fill_sha1_info(p->two);
- 		if (fill_mmfile(&mf1, p->one) < 0 ||
- 				fill_mmfile(&mf2, p->two) < 0)
- 			return error("unable to read files to diff");
  
  		len1 = remove_space(p->one->path, strlen(p->one->path));
  		len2 = remove_space(p->two->path, strlen(p->two->path));
@@@ -4534,12 -4518,17 +4531,19 @@@
  					len2, p->two->path);
  		git_SHA1_Update(&ctx, buffer, len1);
  
+ 		if (diff_header_only)
+ 			continue;
+ 
+ 		if (fill_mmfile(&mf1, p->one) < 0 ||
+ 		    fill_mmfile(&mf2, p->two) < 0)
+ 			return error("unable to read files to diff");
+ 
  		if (diff_filespec_is_binary(p->one) ||
  		    diff_filespec_is_binary(p->two)) {
 -			git_SHA1_Update(&ctx, sha1_to_hex(p->one->sha1), 40);
 -			git_SHA1_Update(&ctx, sha1_to_hex(p->two->sha1), 40);
 +			git_SHA1_Update(&ctx, oid_to_hex(&p->one->oid),
 +					40);
 +			git_SHA1_Update(&ctx, oid_to_hex(&p->two->oid),
 +					40);
  			continue;
  		}
  
@@@ -4556,11 -4545,11 +4560,11 @@@
  	return 0;
  }
  
- int diff_flush_patch_id(struct diff_options *options, unsigned char *sha1)
+ int diff_flush_patch_id(struct diff_options *options, unsigned char *sha1, int diff_header_only)
  {
  	struct diff_queue_struct *q = &diff_queued_diff;
  	int i;
- 	int result = diff_get_patch_id(options, sha1);
+ 	int result = diff_get_patch_id(options, sha1, diff_header_only);
  
  	for (i = 0; i < q->nr; i++)
  		diff_free_filepair(q->queue[i]);
@@@ -4831,7 -4820,7 +4835,7 @@@ static int diff_filespec_check_stat_unm
  	 */
  	if (!DIFF_FILE_VALID(p->one) || /* (1) */
  	    !DIFF_FILE_VALID(p->two) ||
 -	    (p->one->sha1_valid && p->two->sha1_valid) ||
 +	    (p->one->oid_valid && p->two->oid_valid) ||
  	    (p->one->mode != p->two->mode) ||
  	    diff_populate_filespec(p->one, CHECK_SIZE_ONLY) ||
  	    diff_populate_filespec(p->two, CHECK_SIZE_ONLY) ||
@@@ -5127,9 -5116,8 +5131,9 @@@ size_t fill_textconv(struct userdiff_dr
  	if (!driver->textconv)
  		die("BUG: fill_textconv called with non-textconv driver");
  
 -	if (driver->textconv_cache && df->sha1_valid) {
 -		*outbuf = notes_cache_get(driver->textconv_cache, df->sha1,
 +	if (driver->textconv_cache && df->oid_valid) {
 +		*outbuf = notes_cache_get(driver->textconv_cache,
 +					  df->oid.hash,
  					  &size);
  		if (*outbuf)
  			return size;
@@@ -5139,9 -5127,9 +5143,9 @@@
  	if (!*outbuf)
  		die("unable to read files to diff");
  
 -	if (driver->textconv_cache && df->sha1_valid) {
 +	if (driver->textconv_cache && df->oid_valid) {
  		/* ignore errors, as we might be in a readonly repository */
 -		notes_cache_put(driver->textconv_cache, df->sha1, *outbuf,
 +		notes_cache_put(driver->textconv_cache, df->oid.hash, *outbuf,
  				size);
  		/*
  		 * we could save up changes and flush them all at the end,
diff --combined revision.c
index 15873bf24d,233ec72073..8a29cb03c5
--- a/revision.c
+++ b/revision.c
@@@ -846,7 -846,7 +846,7 @@@ static void cherry_pick_list(struct com
  		 */
  		if (left_first != !!(flags & SYMMETRIC_LEFT))
  			continue;
- 		commit->util = add_commit_patch_id(commit, &ids);
+ 		add_commit_patch_id(commit, &ids);
  	}
  
  	/* either cherry_mark or cherry_pick are true */
@@@ -873,21 -873,9 +873,9 @@@
  		id = has_commit_patch_id(commit, &ids);
  		if (!id)
  			continue;
- 		id->seen = 1;
- 		commit->object.flags |= cherry_flag;
- 	}
  
- 	/* Now check the original side for seen ones */
- 	for (p = list; p; p = p->next) {
- 		struct commit *commit = p->item;
- 		struct patch_id *ent;
- 
- 		ent = commit->util;
- 		if (!ent)
- 			continue;
- 		if (ent->seen)
- 			commit->object.flags |= cherry_flag;
- 		commit->util = NULL;
+ 		commit->object.flags |= cherry_flag;
+ 		id->commit->object.flags |= cherry_flag;
  	}
  
  	free_patch_ids(&ids);
@@@ -1425,7 -1413,7 +1413,7 @@@ static void prepare_show_merge(struct r
  		       ce_same_name(ce, active_cache[i+1]))
  			i++;
  	}
 -	free_pathspec(&revs->prune_data);
 +	clear_pathspec(&revs->prune_data);
  	parse_pathspec(&revs->prune_data, PATHSPEC_ALL_MAGIC & ~PATHSPEC_LITERAL,
  		       PATHSPEC_PREFER_FULL | PATHSPEC_LITERAL_PATH, "", prune);
  	revs->limited = 1;
@@@ -1871,8 -1859,6 +1859,8 @@@ static int handle_revision_opt(struct r
  		revs->notes_opt.use_default_notes = 1;
  	} else if (!strcmp(arg, "--show-signature")) {
  		revs->show_signature = 1;
 +	} else if (!strcmp(arg, "--no-show-signature")) {
 +		revs->show_signature = 0;
  	} else if (!strcmp(arg, "--show-linear-break") ||
  		   starts_with(arg, "--show-linear-break=")) {
  		if (starts_with(arg, "--show-linear-break="))
@@@ -1973,16 -1959,16 +1961,16 @@@
  	} else if (!strcmp(arg, "--grep-debug")) {
  		revs->grep_filter.debug = 1;
  	} else if (!strcmp(arg, "--basic-regexp")) {
 -		grep_set_pattern_type_option(GREP_PATTERN_TYPE_BRE, &revs->grep_filter);
 +		revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_BRE;
  	} else if (!strcmp(arg, "--extended-regexp") || !strcmp(arg, "-E")) {
 -		grep_set_pattern_type_option(GREP_PATTERN_TYPE_ERE, &revs->grep_filter);
 +		revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_ERE;
  	} else if (!strcmp(arg, "--regexp-ignore-case") || !strcmp(arg, "-i")) {
  		revs->grep_filter.regflags |= REG_ICASE;
  		DIFF_OPT_SET(&revs->diffopt, PICKAXE_IGNORE_CASE);
  	} else if (!strcmp(arg, "--fixed-strings") || !strcmp(arg, "-F")) {
 -		grep_set_pattern_type_option(GREP_PATTERN_TYPE_FIXED, &revs->grep_filter);
 +		revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_FIXED;
  	} else if (!strcmp(arg, "--perl-regexp")) {
 -		grep_set_pattern_type_option(GREP_PATTERN_TYPE_PCRE, &revs->grep_filter);
 +		revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_PCRE;
  	} else if (!strcmp(arg, "--all-match")) {
  		revs->grep_filter.all_match = 1;
  	} else if (!strcmp(arg, "--invert-grep")) {