1 files changed, 239 insertions, 52 deletions

diff --git a/unpack-trees.c b/unpack-trees.c
index 11c37fbc58..aa15111fef 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -10,6 +10,8 @@
 #include "attr.h"
 #include "split-index.h"
 #include "dir.h"
+#include "submodule.h"
+#include "submodule-config.h"
 
 /*
  * Error messages expected by scripts out of plumbing commands such as
@@ -45,6 +47,9 @@ static const char *unpack_plumbing_errors[NB_UNPACK_TREES_ERROR_TYPES] = {
 
 	/* ERROR_WOULD_LOSE_ORPHANED_REMOVED */
 	"Working tree file '%s' would be removed by sparse checkout update.",
+
+	/* ERROR_WOULD_LOSE_SUBMODULE */
+	"Submodule '%s' cannot checkout new HEAD.",
 };
 
 #define ERRORMSG(o,type) \
@@ -52,6 +57,41 @@ static const char *unpack_plumbing_errors[NB_UNPACK_TREES_ERROR_TYPES] = {
 	  ? ((o)->msgs[(type)])      \
 	  : (unpack_plumbing_errors[(type)]) )
 
+static const char *super_prefixed(const char *path)
+{
+	/*
+	 * It is necessary and sufficient to have two static buffers
+	 * here, as the return value of this function is fed to
+	 * error() using the unpack_*_errors[] templates we see above.
+	 */
+	static struct strbuf buf[2] = {STRBUF_INIT, STRBUF_INIT};
+	static int super_prefix_len = -1;
+	static unsigned idx = ARRAY_SIZE(buf) - 1;
+
+	if (super_prefix_len < 0) {
+		const char *super_prefix = get_super_prefix();
+		if (!super_prefix) {
+			super_prefix_len = 0;
+		} else {
+			int i;
+			for (i = 0; i < ARRAY_SIZE(buf); i++)
+				strbuf_addstr(&buf[i], super_prefix);
+			super_prefix_len = buf[0].len;
+		}
+	}
+
+	if (!super_prefix_len)
+		return path;
+
+	if (++idx >= ARRAY_SIZE(buf))
+		idx = 0;
+
+	strbuf_setlen(&buf[idx], super_prefix_len);
+	strbuf_addstr(&buf[idx], path);
+
+	return buf[idx].buf;
+}
+
 void setup_unpack_trees_porcelain(struct unpack_trees_options *opts,
 				  const char *cmd)
 {
@@ -78,7 +118,7 @@ void setup_unpack_trees_porcelain(struct unpack_trees_options *opts,
 		xstrfmt(msg, cmd, cmd);
 
 	msgs[ERROR_NOT_UPTODATE_DIR] =
-		_("Updating the following directories would lose untracked files in it:\n%s");
+		_("Updating the following directories would lose untracked files in them:\n%s");
 
 	if (!strcmp(cmd, "checkout"))
 		msg = advice_commit_before_merge
@@ -123,9 +163,11 @@ void setup_unpack_trees_porcelain(struct unpack_trees_options *opts,
 	msgs[ERROR_SPARSE_NOT_UPTODATE_FILE] =
 		_("Cannot update sparse checkout: the following entries are not up-to-date:\n%s");
 	msgs[ERROR_WOULD_LOSE_ORPHANED_OVERWRITTEN] =
-		_("The following Working tree files would be overwritten by sparse checkout update:\n%s");
+		_("The following working tree files would be overwritten by sparse checkout update:\n%s");
 	msgs[ERROR_WOULD_LOSE_ORPHANED_REMOVED] =
-		_("The following Working tree files would be removed by sparse checkout update:\n%s");
+		_("The following working tree files would be removed by sparse checkout update:\n%s");
+	msgs[ERROR_WOULD_LOSE_SUBMODULE] =
+		_("Cannot update submodule:\n%s");
 
 	opts->show_all_errors = 1;
 	/* rejected paths may not have a static buffer */
@@ -172,7 +214,7 @@ static int add_rejected_path(struct unpack_trees_options *o,
 			     const char *path)
 {
 	if (!o->show_all_errors)
-		return error(ERRORMSG(o, e), path);
+		return error(ERRORMSG(o, e), super_prefixed(path));
 
 	/*
 	 * Otherwise, insert in a list for future display by
@@ -196,7 +238,7 @@ static void display_error_msgs(struct unpack_trees_options *o)
 			something_displayed = 1;
 			for (i = 0; i < rejects->nr; i++)
 				strbuf_addf(&path, "\t%s\n", rejects->items[i].string);
-			error(ERRORMSG(o, e), path.buf);
+			error(ERRORMSG(o, e), super_prefixed(path.buf));
 			strbuf_release(&path);
 		}
 		string_list_clear(rejects, 0);
@@ -205,12 +247,75 @@ static void display_error_msgs(struct unpack_trees_options *o)
 		fprintf(stderr, _("Aborting\n"));
 }
 
+static int check_submodule_move_head(const struct cache_entry *ce,
+				     const char *old_id,
+				     const char *new_id,
+				     struct unpack_trees_options *o)
+{
+	const struct submodule *sub = submodule_from_ce(ce);
+	if (!sub)
+		return 0;
+
+	switch (sub->update_strategy.type) {
+	case SM_UPDATE_UNSPECIFIED:
+	case SM_UPDATE_CHECKOUT:
+		if (submodule_move_head(ce->name, old_id, new_id, SUBMODULE_MOVE_HEAD_DRY_RUN))
+			return o->gently ? -1 :
+				add_rejected_path(o, ERROR_WOULD_LOSE_SUBMODULE, ce->name);
+		return 0;
+	case SM_UPDATE_NONE:
+		return 0;
+	case SM_UPDATE_REBASE:
+	case SM_UPDATE_MERGE:
+	case SM_UPDATE_COMMAND:
+	default:
+		warning(_("submodule update strategy not supported for submodule '%s'"), ce->name);
+		return -1;
+	}
+}
+
+static void reload_gitmodules_file(struct index_state *index,
+				   struct checkout *state)
+{
+	int i;
+	for (i = 0; i < index->cache_nr; i++) {
+		struct cache_entry *ce = index->cache[i];
+		if (ce->ce_flags & CE_UPDATE) {
+			int r = strcmp(ce->name, ".gitmodules");
+			if (r < 0)
+				continue;
+			else if (r == 0) {
+				submodule_free();
+				checkout_entry(ce, state, NULL);
+				gitmodules_config();
+				git_config(submodule_config, NULL);
+			} else
+				break;
+		}
+	}
+}
+
 /*
  * Unlink the last component and schedule the leading directories for
  * removal, such that empty directories get removed.
  */
 static void unlink_entry(const struct cache_entry *ce)
 {
+	const struct submodule *sub = submodule_from_ce(ce);
+	if (sub) {
+		switch (sub->update_strategy.type) {
+		case SM_UPDATE_UNSPECIFIED:
+		case SM_UPDATE_CHECKOUT:
+		case SM_UPDATE_REBASE:
+		case SM_UPDATE_MERGE:
+			submodule_move_head(ce->name, "HEAD", NULL,
+					    SUBMODULE_MOVE_HEAD_FORCE);
+			break;
+		case SM_UPDATE_NONE:
+		case SM_UPDATE_COMMAND:
+			return; /* Do not touch the submodule. */
+		}
+	}
 	if (!check_leading_path(ce->name, ce_namelen(ce)))
 		return;
 	if (remove_or_warn(ce->ce_mode, ce->name))
@@ -218,29 +323,42 @@ static void unlink_entry(const struct cache_entry *ce)
 	schedule_dir_for_removal(ce->name, ce_namelen(ce));
 }
 
-static struct checkout state;
-static int check_updates(struct unpack_trees_options *o)
+static struct progress *get_progress(struct unpack_trees_options *o)
 {
 	unsigned cnt = 0, total = 0;
+	struct index_state *index = &o->result;
+
+	if (!o->update || !o->verbose_update)
+		return NULL;
+
+	for (; cnt < index->cache_nr; cnt++) {
+		const struct cache_entry *ce = index->cache[cnt];
+		if (ce->ce_flags & (CE_UPDATE | CE_WT_REMOVE))
+			total++;
+	}
+
+	return start_progress_delay(_("Checking out files"),
+				    total, 50, 1);
+}
+
+static int check_updates(struct unpack_trees_options *o)
+{
+	unsigned cnt = 0;
+	int errs = 0;
 	struct progress *progress = NULL;
 	struct index_state *index = &o->result;
+	struct checkout state = CHECKOUT_INIT;
 	int i;
-	int errs = 0;
 
-	if (o->update && o->verbose_update) {
-		for (total = cnt = 0; cnt < index->cache_nr; cnt++) {
-			const struct cache_entry *ce = index->cache[cnt];
-			if (ce->ce_flags & (CE_UPDATE | CE_WT_REMOVE))
-				total++;
-		}
+	state.force = 1;
+	state.quiet = 1;
+	state.refresh_cache = 1;
+	state.istate = index;
 
-		progress = start_progress_delay(_("Checking out files"),
-						total, 50, 1);
-		cnt = 0;
-	}
+	progress = get_progress(o);
 
 	if (o->update)
-		git_attr_set_direction(GIT_ATTR_CHECKOUT, &o->result);
+		git_attr_set_direction(GIT_ATTR_CHECKOUT, index);
 	for (i = 0; i < index->cache_nr; i++) {
 		const struct cache_entry *ce = index->cache[i];
 
@@ -248,12 +366,14 @@ static int check_updates(struct unpack_trees_options *o)
 			display_progress(progress, ++cnt);
 			if (o->update && !o->dry_run)
 				unlink_entry(ce);
-			continue;
 		}
 	}
-	remove_marked_cache_entries(&o->result);
+	remove_marked_cache_entries(index);
 	remove_scheduled_dirs();
 
+	if (should_update_submodules() && o->update && !o->dry_run)
+		reload_gitmodules_file(index, &state);
+
 	for (i = 0; i < index->cache_nr; i++) {
 		struct cache_entry *ce = index->cache[i];
 
@@ -484,12 +604,18 @@ static int switch_cache_bottom(struct traverse_info *info)
 	return ret;
 }
 
+static inline int are_same_oid(struct name_entry *name_j, struct name_entry *name_k)
+{
+	return name_j->oid && name_k->oid && !oidcmp(name_j->oid, name_k->oid);
+}
+
 static int traverse_trees_recursive(int n, unsigned long dirmask,
 				    unsigned long df_conflicts,
 				    struct name_entry *names,
 				    struct traverse_info *info)
 {
 	int i, ret, bottom;
+	int nr_buf = 0;
 	struct tree_desc t[MAX_UNPACK_TREES];
 	void *buf[MAX_UNPACK_TREES];
 	struct traverse_info newinfo;
@@ -506,18 +632,40 @@ static int traverse_trees_recursive(int n, unsigned long dirmask,
 	newinfo.pathlen += tree_entry_len(p) + 1;
 	newinfo.df_conflicts |= df_conflicts;
 
+	/*
+	 * Fetch the tree from the ODB for each peer directory in the
+	 * n commits.
+	 *
+	 * For 2- and 3-way traversals, we try to avoid hitting the
+	 * ODB twice for the same OID.  This should yield a nice speed
+	 * up in checkouts and merges when the commits are similar.
+	 *
+	 * We don't bother doing the full O(n^2) search for larger n,
+	 * because wider traversals don't happen that often and we
+	 * avoid the search setup.
+	 *
+	 * When 2 peer OIDs are the same, we just copy the tree
+	 * descriptor data.  This implicitly borrows the buffer
+	 * data from the earlier cell.
+	 */
 	for (i = 0; i < n; i++, dirmask >>= 1) {
-		const unsigned char *sha1 = NULL;
-		if (dirmask & 1)
-			sha1 = names[i].oid->hash;
-		buf[i] = fill_tree_descriptor(t+i, sha1);
+		if (i > 0 && are_same_oid(&names[i], &names[i - 1]))
+			t[i] = t[i - 1];
+		else if (i > 1 && are_same_oid(&names[i], &names[i - 2]))
+			t[i] = t[i - 2];
+		else {
+			const unsigned char *sha1 = NULL;
+			if (dirmask & 1)
+				sha1 = names[i].oid->hash;
+			buf[nr_buf++] = fill_tree_descriptor(t+i, sha1);
+		}
 	}
 
 	bottom = switch_cache_bottom(&newinfo);
 	ret = traverse_trees(n, t, &newinfo);
 	restore_cache_bottom(&newinfo, bottom);
 
-	for (i = 0; i < n; i++)
+	for (i = 0; i < nr_buf; i++)
 		free(buf[i]);
 
 	return ret;
@@ -625,7 +773,7 @@ static struct cache_entry *create_ce_entry(const struct traverse_info *info, con
 	ce->ce_mode = create_ce_mode(n->mode);
 	ce->ce_flags = create_ce_flags(stage);
 	ce->ce_namelen = len;
-	hashcpy(ce->sha1, n->oid->hash);
+	oidcpy(&ce->oid, n->oid);
 	make_traverse_path(ce->name, info, n);
 
 	return ce;
@@ -1097,12 +1245,6 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 
 	if (len > MAX_UNPACK_TREES)
 		die("unpack_trees takes at most %d trees", MAX_UNPACK_TREES);
-	memset(&state, 0, sizeof(state));
-	state.base_dir = "";
-	state.force = 1;
-	state.quiet = 1;
-	state.refresh_cache = 1;
-	state.istate = &o->result;
 
 	memset(&el, 0, sizeof(el));
 	if (!core_apply_sparse_checkout || !o->update)
@@ -1287,7 +1429,7 @@ static int same(const struct cache_entry *a, const struct cache_entry *b)
 	if ((a->ce_flags | b->ce_flags) & CE_CONFLICTED)
 		return 0;
 	return a->ce_mode == b->ce_mode &&
-	       !hashcmp(a->sha1, b->sha1);
+	       !oidcmp(&a->oid, &b->oid);
 }
 
 
@@ -1317,17 +1459,26 @@ static int verify_uptodate_1(const struct cache_entry *ce,
 	if (!lstat(ce->name, &st)) {
 		int flags = CE_MATCH_IGNORE_VALID|CE_MATCH_IGNORE_SKIP_WORKTREE;
 		unsigned changed = ie_match_stat(o->src_index, ce, &st, flags);
+
+		if (submodule_from_ce(ce)) {
+			int r = check_submodule_move_head(ce,
+				"HEAD", oid_to_hex(&ce->oid), o);
+			if (r)
+				return o->gently ? -1 :
+					add_rejected_path(o, error_type, ce->name);
+			return 0;
+		}
+
 		if (!changed)
 			return 0;
 		/*
-		 * NEEDSWORK: the current default policy is to allow
-		 * submodule to be out of sync wrt the superproject
-		 * index.  This needs to be tightened later for
-		 * submodules that are marked to be automatically
-		 * checked out.
+		 * Historic default policy was to allow submodule to be out
+		 * of sync wrt the superproject index. If the submodule was
+		 * not considered interesting above, we don't care here.
 		 */
 		if (S_ISGITLINK(ce->ce_mode))
 			return 0;
+
 		errno = 0;
 	}
 	if (errno == ENOENT)
@@ -1366,11 +1517,16 @@ static void invalidate_ce_path(const struct cache_entry *ce,
  * Currently, git does not checkout subprojects during a superproject
  * checkout, so it is not going to overwrite anything.
  */
-static int verify_clean_submodule(const struct cache_entry *ce,
+static int verify_clean_submodule(const char *old_sha1,
+				  const struct cache_entry *ce,
 				  enum unpack_trees_error_types error_type,
 				  struct unpack_trees_options *o)
 {
-	return 0;
+	if (!submodule_from_ce(ce))
+		return 0;
+
+	return check_submodule_move_head(ce, old_sha1,
+					 oid_to_hex(&ce->oid), o);
 }
 
 static int verify_clean_subdirectory(const struct cache_entry *ce,
@@ -1386,16 +1542,18 @@ static int verify_clean_subdirectory(const struct cache_entry *ce,
 	struct dir_struct d;
 	char *pathbuf;
 	int cnt = 0;
-	unsigned char sha1[20];
 
-	if (S_ISGITLINK(ce->ce_mode) &&
-	    resolve_gitlink_ref(ce->name, "HEAD", sha1) == 0) {
-		/* If we are not going to update the submodule, then
+	if (S_ISGITLINK(ce->ce_mode)) {
+		unsigned char sha1[20];
+		int sub_head = resolve_gitlink_ref(ce->name, "HEAD", sha1);
+		/*
+		 * If we are not going to update the submodule, then
 		 * we don't care.
 		 */
-		if (!hashcmp(sha1, ce->sha1))
+		if (!sub_head && !hashcmp(sha1, ce->oid.hash))
 			return 0;
-		return verify_clean_submodule(ce, error_type, o);
+		return verify_clean_submodule(sub_head ? NULL : sha1_to_hex(sha1),
+					      ce, error_type, o);
 	}
 
 	/*
@@ -1534,9 +1692,15 @@ static int verify_absent_1(const struct cache_entry *ce,
 		path = xmemdupz(ce->name, len);
 		if (lstat(path, &st))
 			ret = error_errno("cannot stat '%s'", path);
-		else
-			ret = check_ok_to_remove(path, len, DT_UNKNOWN, NULL,
-						 &st, error_type, o);
+		else {
+			if (submodule_from_ce(ce))
+				ret = check_submodule_move_head(ce,
+								oid_to_hex(&ce->oid),
+								NULL, o);
+			else
+				ret = check_ok_to_remove(path, len, DT_UNKNOWN, NULL,
+							 &st, error_type, o);
+		}
 		free(path);
 		return ret;
 	} else if (lstat(ce->name, &st)) {
@@ -1544,6 +1708,10 @@ static int verify_absent_1(const struct cache_entry *ce,
 			return error_errno("cannot stat '%s'", ce->name);
 		return 0;
 	} else {
+		if (submodule_from_ce(ce))
+			return check_submodule_move_head(ce, oid_to_hex(&ce->oid),
+							 NULL, o);
+
 		return check_ok_to_remove(ce->name, ce_namelen(ce),
 					  ce_to_dtype(ce), ce, &st,
 					  error_type, o);
@@ -1599,6 +1767,15 @@ static int merged_entry(const struct cache_entry *ce,
 			return -1;
 		}
 		invalidate_ce_path(merge, o);
+
+		if (submodule_from_ce(ce)) {
+			int ret = check_submodule_move_head(ce, NULL,
+							    oid_to_hex(&ce->oid),
+							    o);
+			if (ret)
+				return ret;
+		}
+
 	} else if (!(old->ce_flags & CE_CONFLICTED)) {
 		/*
 		 * See if we can re-use the old CE directly?
@@ -1619,6 +1796,14 @@ static int merged_entry(const struct cache_entry *ce,
 			update |= old->ce_flags & (CE_SKIP_WORKTREE | CE_NEW_SKIP_WORKTREE);
 			invalidate_ce_path(old, o);
 		}
+
+		if (submodule_from_ce(ce)) {
+			int ret = check_submodule_move_head(ce, oid_to_hex(&old->oid),
+							    oid_to_hex(&ce->oid),
+							    o);
+			if (ret)
+				return ret;
+		}
 	} else {
 		/*
 		 * Previously unmerged entry left as an existence
@@ -1665,7 +1850,7 @@ static void show_stage_entry(FILE *o,
 		fprintf(o, "%s%06o %s %d\t%s\n",
 			label,
 			ce->ce_mode,
-			sha1_to_hex(ce->sha1),
+			oid_to_hex(&ce->oid),
 			ce_stage(ce),
 			ce->name);
 }
@@ -1919,7 +2104,9 @@ int bind_merge(const struct cache_entry * const *src,
 			     o->merge_size);
 	if (a && old)
 		return o->gently ? -1 :
-			error(ERRORMSG(o, ERROR_BIND_OVERLAP), a->name, old->name);
+			error(ERRORMSG(o, ERROR_BIND_OVERLAP),
+			      super_prefixed(a->name),
+			      super_prefixed(old->name));
 	if (!a)
 		return keep_entry(old, o);
 	else