DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org 08D86606A32E
DKIM2-Signature: i=1; m=1; t=1794014813; d=pobox.com;
	mf=PGdpdHN0ZXJAcG9ib3guY29tPg==;
	rt=PGdpdEB2Z2VyLmtlcm5lbC5vcmc+;
	s=fm2:rsa-sha256:bndXvoMHn7pbbImw7wlW5RKcDAnGnyOQswcxkH7poVPeAYv
	ASUGN/2XklTvwaUNnMzr3h6rBdEYFo45IIf7JrtUYTdKJqt8WowubT+Ud1p111t4
	LyjT0tWaHqQHNw9hL/KKj2aUMyHz0U/x4nmCGFHN6GBbNwciTj5PKTMBUwdan6lx
	8PywMCiJflTf7k9jRdcI9B07QazK3S0L9o9a4lppZQ1YHl9os/ytiL1qkx+N7DBn
	feiP5+0aLb5Cn+Y+nkcBCkLBrDBeKyz74FlYAb5AqpAEWkYrfg4CEp3pOcib2CnD
	XQmckRIRZS4FuO++M47mNDvJEkyMEJ3AmDjT0Nw==;
Message-Instance: m=1; h=sha256:TkTApYMeN2NfCgvsJpE64JgruNCS6/qCocpgrdb5zLE=:D7xMoGc9k4BLTlKxMCh1xEp2GjSnaLy1cSJcUcPjHRw=;
Feedback-ID: if26b431b:Fastmail
From: Junio C Hamano <gitster@pobox.com>
To: git@vger.kernel.org
Subject: [PATCH 1/2] unpack-trees: lose USE_THE_REPOSITORY
Date: Fri, 06 Nov 2026 17:26:52 -0800
Message-ID: <xmqqtsltbfdv.fsf@gitster.g>
User-Agent: Gnus/5.13 (Gnus v5.13)
Precedence: list
MIME-Version: 1.0
Content-Type: text/plain

This file defines a set of fairly low level functions to implement
merge and checkout behaviour, many of which depended on and can only
work with the_repository.

Two key data structures passed around in the code paths, "struct
unpack_trees_options" and "struct index_state", both have a pointer
to the repository instance, and we can use it to make it work on an
arbitrary repository, not just the_repository.

In any correctly written clients of this library file, the
repository instance that is pointed at by these two structs MUST be
the same one.  For now, make sure that is the case (and otherwise
BUG out) by introducing a unpack_repo() helper function that takes
these two structures (when available) and returns the repository.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
---

 * I wrote this change when I ranted in

   https://lore.kernel.org/git/xmqq33tdcuub.fsf@gitster.g/

   on 'seen', and "git checkout -m --detach master" was sufficient
   to build and start a new branch based on 'master' and there
   wasn't any need for adjustment.  All tests seem to pass.

 unpack-trees.c | 94 ++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 76 insertions(+), 18 deletions(-)

diff --git a/unpack-trees.c b/unpack-trees.c
index d6a859420f..79341d7fa6 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -1,4 +1,3 @@
-#define USE_THE_REPOSITORY_VARIABLE
 #define DISABLE_SIGN_COMPARE_WARNINGS
 
 #include "git-compat-util.h"
@@ -82,6 +81,56 @@ static const char *unpack_plumbing_errors[NB_UNPACK_TREES_WARNING_TYPES] = {
 	  ? ((o)->internal.msgs[(type)])      \
 	  : (unpack_plumbing_errors[(type)]) )
 
+
+/*
+ * Some functions in these code paths get unpack_trees_options, which
+ * has up to two istates, and some get an istate.  These istates can
+ * be used to find the repository to be used for this operation.
+ *
+ * As these are all working on the same repository, they must match.
+ * For now, with a super paranoid check, make sure all potential
+ * sources of the information match before using it.
+ *
+ * Once this proves working well, we could just use the first one we
+ * find in a production setting.
+ */
+static struct repository *unpack_repo(struct index_state *istate,
+				      struct unpack_trees_options *o)
+{
+	struct repository *repo = NULL;
+	const char *camefrom = NULL;
+
+	if (istate) {
+		if (!istate->repo)
+			BUG("istate->repo == NULL");
+		repo = istate->repo;
+		camefrom = "istate->repo";
+	}
+	if (o) {
+		if (o->src_index) {
+			if (!o->src_index->repo)
+				BUG("o->src_index->repo == NULL");
+			if (repo && repo != o->src_index->repo)
+				BUG("%s != o->src_index->repo", camefrom);
+			repo = o->src_index->repo;
+			camefrom = "o->src_index->repo";
+		}
+
+		if (o->dst_index) {
+			if (!o->dst_index->repo)
+				BUG("o->dst_index->repo == NULL");
+			if (repo && repo != o->dst_index->repo)
+				BUG("%s != o->dst_index->repo", camefrom);
+			repo = o->dst_index->repo;
+		}
+	}
+	if (!repo)
+		BUG("no repository for unpack_trees()?");
+	return repo;
+
+}
+
+
 static const char *super_prefixed(const char *path, const char *super_prefix)
 {
 	/*
@@ -345,15 +394,16 @@ static void load_gitmodules_file(struct index_state *index,
 				 struct checkout *state)
 {
 	int pos = index_name_pos(index, GITMODULES_FILE, strlen(GITMODULES_FILE));
+	struct repository *repo = unpack_repo(index, NULL);
 
 	if (pos >= 0) {
 		struct cache_entry *ce = index->cache[pos];
 		if (!state && ce->ce_flags & CE_WT_REMOVE) {
-			repo_read_gitmodules(the_repository, 0);
+			repo_read_gitmodules(repo, 0);
 		} else if (state && (ce->ce_flags & CE_UPDATE)) {
-			submodule_free(the_repository);
+			submodule_free(repo);
 			checkout_entry(ce, state, NULL, NULL);
-			repo_read_gitmodules(the_repository, 0);
+			repo_read_gitmodules(repo, 0);
 		}
 	}
 }
@@ -362,6 +412,7 @@ static struct progress *get_progress(struct unpack_trees_options *o,
 				     struct index_state *index)
 {
 	unsigned cnt = 0, total = 0;
+	struct repository *repo = unpack_repo(index, o);
 
 	if (!o->update || !o->verbose_update)
 		return NULL;
@@ -372,7 +423,7 @@ static struct progress *get_progress(struct unpack_trees_options *o,
 			total++;
 	}
 
-	return start_delayed_progress(the_repository,
+	return start_delayed_progress(repo,
 				      _("Updating files"), total);
 }
 
@@ -430,6 +481,7 @@ static int check_updates(struct unpack_trees_options *o,
 	struct progress *progress;
 	struct checkout state = CHECKOUT_INIT;
 	int i, pc_workers, pc_threshold;
+	struct repository *repo = unpack_repo(index, o);
 
 	trace_performance_enter();
 	state.super_prefix = o->super_prefix;
@@ -473,7 +525,7 @@ static int check_updates(struct unpack_trees_options *o,
 	if (should_update_submodules())
 		load_gitmodules_file(index, &state);
 
-	if (repo_has_promisor_remote(the_repository))
+	if (repo_has_promisor_remote(repo))
 		/*
 		 * Prefetch the objects that are to be checked out in the loop
 		 * below.
@@ -879,6 +931,7 @@ static int traverse_trees_recursive(int n, unsigned long dirmask,
 	struct traverse_info newinfo;
 	struct name_entry *p;
 	int nr_entries;
+	struct repository *repo = unpack_repo(NULL, o);
 
 	nr_entries = all_trees_same_as_cache_tree(n, dirmask, names, info);
 	if (nr_entries > 0) {
@@ -940,7 +993,7 @@ static int traverse_trees_recursive(int n, unsigned long dirmask,
 			const struct object_id *oid = NULL;
 			if (dirmask & 1)
 				oid = &names[i].oid;
-			buf[nr_buf++] = fill_tree_descriptor(the_repository, t + i, oid);
+			buf[nr_buf++] = fill_tree_descriptor(repo, t + i, oid);
 		}
 	}
 
@@ -1773,24 +1826,25 @@ static int clear_ce_flags(struct index_state *istate,
 	static struct strbuf prefix = STRBUF_INIT;
 	char label[100];
 	int rval;
+	struct repository *repo = unpack_repo(istate, NULL);
 
 	strbuf_reset(&prefix);
 	if (show_progress)
 		istate->progress = start_delayed_progress(
-					the_repository,
+					repo,
 					_("Updating index flags"),
 					istate->cache_nr);
 
 	xsnprintf(label, sizeof(label), "clear_ce_flags(0x%08lx,0x%08lx)",
 		  (unsigned long)select_mask, (unsigned long)clear_mask);
-	trace2_region_enter("unpack_trees", label, istate->repo);
+	trace2_region_enter("unpack_trees", label, repo);
 	rval = clear_ce_flags_1(istate,
 				istate->cache,
 				istate->cache_nr,
 				&prefix,
 				select_mask, clear_mask,
 				pl, 0, 0);
-	trace2_region_leave("unpack_trees", label, istate->repo);
+	trace2_region_leave("unpack_trees", label, repo);
 
 	stop_progress(&istate->progress);
 	return rval;
@@ -1885,13 +1939,13 @@ static int verify_absent(const struct cache_entry *,
  */
 int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options *o)
 {
-	struct repository *repo = o->src_index->repo;
+	struct repository *repo = unpack_repo(NULL, o);
 	int i, ret;
 	static struct cache_entry *dfc;
 	struct pattern_list pl;
 	int free_pattern_list = 0;
 	struct dir_struct dir = DIR_INIT;
-	struct repo_config_values *cfg = repo_config_values(the_repository);
+	struct repo_config_values *cfg = repo_config_values(repo);
 
 	if (o->reset == UNPACK_RESET_INVALID)
 		BUG("o->reset had a value of 1; should be UNPACK_TREES_*_UNTRACKED");
@@ -1936,7 +1990,7 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 		populate_from_existing_patterns(o, &pl);
 	}
 
-	index_state_init(&o->internal.result, o->src_index->repo);
+	index_state_init(&o->internal.result, repo);
 	o->internal.result.initialized = 1;
 	o->internal.result.timestamp.sec = o->src_index->timestamp.sec;
 	o->internal.result.timestamp.nsec = o->src_index->timestamp.nsec;
@@ -2081,7 +2135,7 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 		move_index_extensions(&o->internal.result, o->src_index);
 		if (!ret) {
 			if (git_env_bool("GIT_TEST_CHECK_CACHE_TREE", 0) &&
-			    cache_tree_verify(the_repository,
+			    cache_tree_verify(repo,
 					      &o->internal.result) < 0) {
 				ret = -1;
 				goto done;
@@ -2137,10 +2191,11 @@ enum update_sparsity_result update_sparsity(struct unpack_trees_options *o,
 	int i;
 	unsigned old_show_all_errors;
 	int free_pattern_list = 0;
+	struct repository *repo = unpack_repo(NULL, o);
 
 	old_show_all_errors = o->internal.show_all_errors;
 	o->internal.show_all_errors = 1;
-	index_state_init(&o->internal.result, o->src_index->repo);
+	index_state_init(&o->internal.result, repo);
 
 	/* Sanity checks */
 	if (!o->update || o->index_only || o->skip_sparse_checkout)
@@ -2333,10 +2388,11 @@ static int verify_clean_subdirectory(const struct cache_entry *ce,
 	struct dir_struct d;
 	char *pathbuf;
 	int cnt = 0;
+	struct repository *repo = unpack_repo(NULL, o);
 
 	if (S_ISGITLINK(ce->ce_mode)) {
 		struct object_id oid;
-		int sub_head = repo_resolve_gitlink_ref(the_repository, ce->name,
+		int sub_head = repo_resolve_gitlink_ref(repo, ce->name,
 							"HEAD", &oid);
 		/*
 		 * If we are not going to update the submodule, then
@@ -2424,6 +2480,7 @@ static int check_ok_to_remove(const char *name, int len, int dtype,
 			      struct unpack_trees_options *o)
 {
 	const struct cache_entry *result;
+	struct repository *repo = unpack_repo(NULL, o);
 
 	/*
 	 * It may be that the 'lstat()' succeeded even though
@@ -2432,7 +2489,7 @@ static int check_ok_to_remove(const char *name, int len, int dtype,
 	 *
 	 * Ignore that lstat() if it matches.
 	 */
-	if (repo_ignore_case(the_repository) && icase_exists(o, name, len, st))
+	if (repo_ignore_case(repo) && icase_exists(o, name, len, st))
 		return 0;
 
 	if (o->internal.dir &&
@@ -2652,6 +2709,7 @@ static int merged_sparse_dir(const struct cache_entry * const *src, int n,
 	void * tree_bufs[MAX_UNPACK_TREES + 1];
 	struct traverse_info info;
 	int i, ret;
+	struct repository *repo = unpack_repo(NULL, o);
 
 	/*
 	 * Create the tree traversal information for traversing into *only* the
@@ -2665,7 +2723,7 @@ static int merged_sparse_dir(const struct cache_entry * const *src, int n,
 
 	/* Get the tree descriptors of the sparse directory in each of the merging trees */
 	for (i = 0; i < n; i++)
-		tree_bufs[i] = fill_tree_descriptor(o->src_index->repo, &t[i],
+		tree_bufs[i] = fill_tree_descriptor(repo, &t[i],
 						    src[i] && !is_null_oid(&src[i]->oid) ? &src[i]->oid : NULL);
 
 	ret = traverse_trees(o->src_index, n, t, &info);
-- 
2.56.0-599-geab4b2c7f0