Performance optimization for detection of modified submodules

In the worst case is_submodule_modified() got called three times for
each submodule. The information we got from scanning the whole
submodule tree the first time can be reused instead.

New parameters have been added to diff_change() and diff_addremove(),
the information is stored in a new member of struct diff_filespec. Its
value is then reused instead of calling is_submodule_modified() again.

When no explicit "-dirty" is needed in the output the call to
is_submodule_modified() is not necessary when the submodules HEAD
already disagrees with the ref of the superproject, as this alone
marks it as modified. To achieve that, get_stat_data() got an extra
argument.

Signed-off-by: Jens Lehmann <Jens.Lehmann@web.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 31 insertions, 15 deletions

diff --git a/diff-lib.c b/diff-lib.c
index 9cdf6da..23e180e 100644
--- a/diff-lib.c
+++ b/diff-lib.c
@@ -73,6 +73,7 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 		unsigned int oldmode, newmode;
 		struct cache_entry *ce = active_cache[i];
 		int changed;
+		unsigned dirty_submodule = 0;
 
 		if (DIFF_OPT_TST(&revs->diffopt, QUICK) &&
 			DIFF_OPT_TST(&revs->diffopt, HAS_CHANGES))
@@ -173,12 +174,16 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 			if (silent_on_removed)
 				continue;
 			diff_addremove(&revs->diffopt, '-', ce->ce_mode,
-				       ce->sha1, ce->name);
+				       ce->sha1, ce->name, 0);
 			continue;
 		}
 		changed = ce_match_stat(ce, &st, ce_option);
-		if (S_ISGITLINK(ce->ce_mode) && !changed)
-			changed = is_submodule_modified(ce->name);
+		if (S_ISGITLINK(ce->ce_mode)
+		    && (!changed || (revs->diffopt.output_format & DIFF_FORMAT_PATCH))
+		    && is_submodule_modified(ce->name)) {
+			changed = 1;
+			dirty_submodule = 1;
+		}
 		if (!changed) {
 			ce_mark_uptodate(ce);
 			if (!DIFF_OPT_TST(&revs->diffopt, FIND_COPIES_HARDER))
@@ -188,7 +193,7 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 		newmode = ce_mode_from_stat(ce, st.st_mode);
 		diff_change(&revs->diffopt, oldmode, newmode,
 			    ce->sha1, (changed ? null_sha1 : ce->sha1),
-			    ce->name);
+			    ce->name, 0, dirty_submodule);
 
 	}
 	diffcore_std(&revs->diffopt);
@@ -204,16 +209,18 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 static void diff_index_show_file(struct rev_info *revs,
 				 const char *prefix,
 				 struct cache_entry *ce,
-				 const unsigned char *sha1, unsigned int mode)
+				 const unsigned char *sha1, unsigned int mode,
+				 unsigned dirty_submodule)
 {
 	diff_addremove(&revs->diffopt, prefix[0], mode,
-		       sha1, ce->name);
+		       sha1, ce->name, dirty_submodule);
 }
 
 static int get_stat_data(struct cache_entry *ce,
 			 const unsigned char **sha1p,
 			 unsigned int *modep,
-			 int cached, int match_missing)
+			 int cached, int match_missing,
+			 unsigned *dirty_submodule, int output_format)
 {
 	const unsigned char *sha1 = ce->sha1;
 	unsigned int mode = ce->ce_mode;
@@ -233,8 +240,13 @@ static int get_stat_data(struct cache_entry *ce,
 			return -1;
 		}
 		changed = ce_match_stat(ce, &st, 0);
-		if (changed
-		    || (S_ISGITLINK(ce->ce_mode) && is_submodule_modified(ce->name))) {
+		if (S_ISGITLINK(ce->ce_mode)
+		    && (!changed || (output_format & DIFF_FORMAT_PATCH))
+		    && is_submodule_modified(ce->name)) {
+			changed = 1;
+			*dirty_submodule = 1;
+		}
+		if (changed) {
 			mode = ce_mode_from_stat(ce, st.st_mode);
 			sha1 = null_sha1;
 		}
@@ -251,15 +263,17 @@ static void show_new_file(struct rev_info *revs,
 {
 	const unsigned char *sha1;
 	unsigned int mode;
+	unsigned dirty_submodule = 0;
 
 	/*
 	 * New file in the index: it might actually be different in
 	 * the working copy.
 	 */
-	if (get_stat_data(new, &sha1, &mode, cached, match_missing) < 0)
+	if (get_stat_data(new, &sha1, &mode, cached, match_missing,
+	    &dirty_submodule, revs->diffopt.output_format) < 0)
 		return;
 
-	diff_index_show_file(revs, "+", new, sha1, mode);
+	diff_index_show_file(revs, "+", new, sha1, mode, dirty_submodule);
 }
 
 static int show_modified(struct rev_info *revs,
@@ -270,11 +284,13 @@ static int show_modified(struct rev_info *revs,
 {
 	unsigned int mode, oldmode;
 	const unsigned char *sha1;
+	unsigned dirty_submodule = 0;
 
-	if (get_stat_data(new, &sha1, &mode, cached, match_missing) < 0) {
+	if (get_stat_data(new, &sha1, &mode, cached, match_missing,
+			  &dirty_submodule, revs->diffopt.output_format) < 0) {
 		if (report_missing)
 			diff_index_show_file(revs, "-", old,
-					     old->sha1, old->ce_mode);
+					     old->sha1, old->ce_mode, 0);
 		return -1;
 	}
 
@@ -309,7 +325,7 @@ static int show_modified(struct rev_info *revs,
 		return 0;
 
 	diff_change(&revs->diffopt, oldmode, mode,
-		    old->sha1, sha1, old->name);
+		    old->sha1, sha1, old->name, 0, dirty_submodule);
 	return 0;
 }
 
@@ -356,7 +372,7 @@ static void do_oneway_diff(struct unpack_trees_options *o,
 	 * Something removed from the tree?
 	 */
 	if (!idx) {
-		diff_index_show_file(revs, "-", tree, tree->sha1, tree->ce_mode);
+		diff_index_show_file(revs, "-", tree, tree->sha1, tree->ce_mode, 0);
 		return;
 	}