Merge branch 'nd/unpack-trees-with-cache-tree'

The unpack_trees() API used in checking out a branch and merging
walks one or more trees along with the index.  When the cache-tree
in the index tells us that we are walking a tree whose flattened
contents is known (i.e. matches a span in the index), as linearly
scanning a span in the index is much more efficient than having to
open tree objects recursively and listing their entries, the walk
can be optimized, which is done in this topic.

* nd/unpack-trees-with-cache-tree:
  Document update for nd/unpack-trees-with-cache-tree
  cache-tree: verify valid cache-tree in the test suite
  unpack-trees: add missing cache invalidation
  unpack-trees: reuse (still valid) cache-tree from src_index
  unpack-trees: reduce malloc in cache-tree walk
  unpack-trees: optimize walking same trees with cache-tree
  unpack-trees: add performance tracing
  trace.h: support nested performance tracing

12 files changed, 344 insertions, 22 deletions

diff --git a/cache-tree.c b/cache-tree.c
index 16ea022c46..490a25adf0 100644
--- a/cache-tree.c
+++ b/cache-tree.c
@@ -4,6 +4,7 @@
 #include "tree-walk.h"
 #include "cache-tree.h"
 #include "object-store.h"
+#include "replace-object.h"
 
 #ifndef DEBUG
 #define DEBUG 0
@@ -433,7 +434,9 @@ int cache_tree_update(struct index_state *istate, int flags)
 
 	if (i)
 		return i;
+	trace_performance_enter();
 	i = update_one(it, cache, entries, "", 0, &skip, flags);
+	trace_performance_leave("cache_tree_update");
 	if (i < 0)
 		return i;
 	istate->cache_changed |= CACHE_TREE_CHANGED;
@@ -718,3 +721,80 @@ int cache_tree_matches_traversal(struct cache_tree *root,
 		return it->entry_count;
 	return 0;
 }
+
+static void verify_one(struct index_state *istate,
+		       struct cache_tree *it,
+		       struct strbuf *path)
+{
+	int i, pos, len = path->len;
+	struct strbuf tree_buf = STRBUF_INIT;
+	struct object_id new_oid;
+
+	for (i = 0; i < it->subtree_nr; i++) {
+		strbuf_addf(path, "%s/", it->down[i]->name);
+		verify_one(istate, it->down[i]->cache_tree, path);
+		strbuf_setlen(path, len);
+	}
+
+	if (it->entry_count < 0 ||
+	    /* no verification on tests (t7003) that replace trees */
+	    lookup_replace_object(the_repository, &it->oid) != &it->oid)
+		return;
+
+	if (path->len) {
+		pos = index_name_pos(istate, path->buf, path->len);
+		pos = -pos - 1;
+	} else {
+		pos = 0;
+	}
+
+	i = 0;
+	while (i < it->entry_count) {
+		struct cache_entry *ce = istate->cache[pos + i];
+		const char *slash;
+		struct cache_tree_sub *sub = NULL;
+		const struct object_id *oid;
+		const char *name;
+		unsigned mode;
+		int entlen;
+
+		if (ce->ce_flags & (CE_STAGEMASK | CE_INTENT_TO_ADD | CE_REMOVE))
+			BUG("%s with flags 0x%x should not be in cache-tree",
+			    ce->name, ce->ce_flags);
+		name = ce->name + path->len;
+		slash = strchr(name, '/');
+		if (slash) {
+			entlen = slash - name;
+			sub = find_subtree(it, ce->name + path->len, entlen, 0);
+			if (!sub || sub->cache_tree->entry_count < 0)
+				BUG("bad subtree '%.*s'", entlen, name);
+			oid = &sub->cache_tree->oid;
+			mode = S_IFDIR;
+			i += sub->cache_tree->entry_count;
+		} else {
+			oid = &ce->oid;
+			mode = ce->ce_mode;
+			entlen = ce_namelen(ce) - path->len;
+			i++;
+		}
+		strbuf_addf(&tree_buf, "%o %.*s%c", mode, entlen, name, '\0');
+		strbuf_add(&tree_buf, oid->hash, the_hash_algo->rawsz);
+	}
+	hash_object_file(tree_buf.buf, tree_buf.len, tree_type, &new_oid);
+	if (oidcmp(&new_oid, &it->oid))
+		BUG("cache-tree for path %.*s does not match. "
+		    "Expected %s got %s", len, path->buf,
+		    oid_to_hex(&new_oid), oid_to_hex(&it->oid));
+	strbuf_setlen(path, len);
+	strbuf_release(&tree_buf);
+}
+
+void cache_tree_verify(struct index_state *istate)
+{
+	struct strbuf path = STRBUF_INIT;
+
+	if (!istate->cache_tree)
+		return;
+	verify_one(istate, istate->cache_tree, &path);
+	strbuf_release(&path);
+}
diff --git a/cache-tree.h b/cache-tree.h
index fc0c842e77..0ab6784ffe 100644
--- a/cache-tree.h
+++ b/cache-tree.h
@@ -32,6 +32,7 @@ struct cache_tree *cache_tree_read(const char *buffer, unsigned long size);
 
 int cache_tree_fully_valid(struct cache_tree *);
 int cache_tree_update(struct index_state *, int);
+void cache_tree_verify(struct index_state *);
 
 /* bitmasks to write_cache_as_tree flags */
 #define WRITE_TREE_MISSING_OK 1
diff --git a/diff-lib.c b/diff-lib.c
index 88a98b1c06..70cddbf436 100644
--- a/diff-lib.c
+++ b/diff-lib.c
@@ -518,11 +518,11 @@ static int diff_cache(struct rev_info *revs,
 int run_diff_index(struct rev_info *revs, int cached)
 {
 	struct object_array_entry *ent;
-	uint64_t start = getnanotime();
 
 	if (revs->pending.nr != 1)
 		BUG("run_diff_index must be passed exactly one tree");
 
+	trace_performance_enter();
 	ent = revs->pending.objects;
 	if (diff_cache(revs, &ent->item->oid, ent->name, cached))
 		exit(128);
@@ -531,7 +531,7 @@ int run_diff_index(struct rev_info *revs, int cached)
 	diffcore_fix_diff_index(&revs->diffopt);
 	diffcore_std(&revs->diffopt);
 	diff_flush(&revs->diffopt);
-	trace_performance_since(start, "diff-index");
+	trace_performance_leave("diff-index");
 	return 0;
 }
 
diff --git a/dir.c b/dir.c
index aceb0d4869..995b8e3261 100644
--- a/dir.c
+++ b/dir.c
@@ -2268,10 +2268,13 @@ int read_directory(struct dir_struct *dir, struct index_state *istate,
 		   const char *path, int len, const struct pathspec *pathspec)
 {
 	struct untracked_cache_dir *untracked;
-	uint64_t start = getnanotime();
 
-	if (has_symlink_leading_path(path, len))
+	trace_performance_enter();
+
+	if (has_symlink_leading_path(path, len)) {
+		trace_performance_leave("read directory %.*s", len, path);
 		return dir->nr;
+	}
 
 	untracked = validate_untracked_cache(dir, len, pathspec);
 	if (!untracked)
@@ -2307,7 +2310,7 @@ int read_directory(struct dir_struct *dir, struct index_state *istate,
 		dir->nr = i;
 	}
 
-	trace_performance_since(start, "read directory %.*s", len, path);
+	trace_performance_leave("read directory %.*s", len, path);
 	if (dir->untracked) {
 		static int force_untracked_cache = -1;
 		static struct trace_key trace_untracked_stats = TRACE_KEY_INIT(UNTRACKED_STATS);
diff --git a/name-hash.c b/name-hash.c
index 163849831c..1fcda73cb3 100644
--- a/name-hash.c
+++ b/name-hash.c
@@ -578,10 +578,10 @@ static void threaded_lazy_init_name_hash(
 
 static void lazy_init_name_hash(struct index_state *istate)
 {
-	uint64_t start = getnanotime();
 
 	if (istate->name_hash_initialized)
 		return;
+	trace_performance_enter();
 	hashmap_init(&istate->name_hash, cache_entry_cmp, NULL, istate->cache_nr);
 	hashmap_init(&istate->dir_hash, dir_entry_cmp, NULL, istate->cache_nr);
 
@@ -602,7 +602,7 @@ static void lazy_init_name_hash(struct index_state *istate)
 	}
 
 	istate->name_hash_initialized = 1;
-	trace_performance_since(start, "initialize name hash");
+	trace_performance_leave("initialize name hash");
 }
 
 /*
diff --git a/preload-index.c b/preload-index.c
index 71cd2437a3..f7365761f4 100644
--- a/preload-index.c
+++ b/preload-index.c
@@ -78,7 +78,6 @@ static void preload_index(struct index_state *index,
 {
 	int threads, i, work, offset;
 	struct thread_data data[MAX_PARALLEL];
-	uint64_t start = getnanotime();
 
 	if (!core_preload_index)
 		return;
@@ -88,6 +87,7 @@ static void preload_index(struct index_state *index,
 		threads = 2;
 	if (threads < 2)
 		return;
+	trace_performance_enter();
 	if (threads > MAX_PARALLEL)
 		threads = MAX_PARALLEL;
 	offset = 0;
@@ -109,7 +109,7 @@ static void preload_index(struct index_state *index,
 		if (pthread_join(p->pthread, NULL))
 			die("unable to join threaded lstat");
 	}
-	trace_performance_since(start, "preload index");
+	trace_performance_leave("preload index");
 }
 #endif
 
diff --git a/read-cache.c b/read-cache.c
index 7b1354d759..d7b617f320 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -1476,8 +1476,8 @@ int refresh_index(struct index_state *istate, unsigned int flags,
 	const char *typechange_fmt;
 	const char *added_fmt;
 	const char *unmerged_fmt;
-	uint64_t start = getnanotime();
 
+	trace_performance_enter();
 	modified_fmt = (in_porcelain ? "M\t%s\n" : "%s: needs update\n");
 	deleted_fmt = (in_porcelain ? "D\t%s\n" : "%s: needs update\n");
 	typechange_fmt = (in_porcelain ? "T\t%s\n" : "%s needs update\n");
@@ -1547,7 +1547,7 @@ int refresh_index(struct index_state *istate, unsigned int flags,
 
 		replace_index_entry(istate, i, new_entry);
 	}
-	trace_performance_since(start, "refresh index");
+	trace_performance_leave("refresh index");
 	return has_errors;
 }
 
@@ -2002,7 +2002,6 @@ static void freshen_shared_index(const char *shared_index, int warn)
 int read_index_from(struct index_state *istate, const char *path,
 		    const char *gitdir)
 {
-	uint64_t start = getnanotime();
 	struct split_index *split_index;
 	int ret;
 	char *base_oid_hex;
@@ -2012,8 +2011,9 @@ int read_index_from(struct index_state *istate, const char *path,
 	if (istate->initialized)
 		return istate->cache_nr;
 
+	trace_performance_enter();
 	ret = do_read_index(istate, path, 0);
-	trace_performance_since(start, "read cache %s", path);
+	trace_performance_leave("read cache %s", path);
 
 	split_index = istate->split_index;
 	if (!split_index || is_null_oid(&split_index->base_oid)) {
@@ -2021,6 +2021,7 @@ int read_index_from(struct index_state *istate, const char *path,
 		return ret;
 	}
 
+	trace_performance_enter();
 	if (split_index->base)
 		discard_index(split_index->base);
 	else
@@ -2037,8 +2038,8 @@ int read_index_from(struct index_state *istate, const char *path,
 	freshen_shared_index(base_path, 0);
 	merge_base_index(istate);
 	post_read_index_from(istate);
-	trace_performance_since(start, "read cache %s", base_path);
 	free(base_path);
+	trace_performance_leave("read cache %s", base_path);
 	return ret;
 }
 
@@ -2743,6 +2744,9 @@ int write_locked_index(struct index_state *istate, struct lock_file *lock,
 	int new_shared_index, ret;
 	struct split_index *si = istate->split_index;
 
+	if (git_env_bool("GIT_TEST_CHECK_CACHE_TREE", 0))
+		cache_tree_verify(istate);
+
 	if ((flags & SKIP_IF_UNCHANGED) && !istate->cache_changed) {
 		if (flags & COMMIT_LOCK)
 			rollback_lock_file(lock);
@@ -2939,6 +2943,8 @@ void move_index_extensions(struct index_state *dst, struct index_state *src)
 {
 	dst->untracked = src->untracked;
 	src->untracked = NULL;
+	dst->cache_tree = src->cache_tree;
+	src->cache_tree = NULL;
 }
 
 struct cache_entry *dup_cache_entry(const struct cache_entry *ce,
diff --git a/t/README b/t/README
index 9028b47d92..204b9f4cc5 100644
--- a/t/README
+++ b/t/README
@@ -319,6 +319,10 @@ GIT_TEST_OE_DELTA_SIZE=<n> exercises the uncomon pack-objects code
 path where deltas larger than this limit require extra memory
 allocation for bookkeeping.
 
+GIT_TEST_VALIDATE_INDEX_CACHE_ENTRIES=<boolean> checks that cache-tree
+records are valid when the index is written out or after a merge. This
+is mostly to catch missing invalidation. Default is true.
+
 Naming Tests
 ------------
 
diff --git a/t/test-lib.sh b/t/test-lib.sh
index 44288cbb59..3f95bfda60 100644
--- a/t/test-lib.sh
+++ b/t/test-lib.sh
@@ -1083,6 +1083,12 @@ else
 	test_set_prereq C_LOCALE_OUTPUT
 fi
 
+if test -z "$GIT_TEST_CHECK_CACHE_TREE"
+then
+	GIT_TEST_CHECK_CACHE_TREE=true
+	export GIT_TEST_CHECK_CACHE_TREE
+fi
+
 test_lazy_prereq PIPE '
 	# test whether the filesystem supports FIFOs
 	test_have_prereq !MINGW,!CYGWIN &&
diff --git a/trace.c b/trace.c
index fc623e91fd..fa4a2e7120 100644
--- a/trace.c
+++ b/trace.c
@@ -176,10 +176,30 @@ void trace_strbuf_fl(const char *file, int line, struct trace_key *key,
 	strbuf_release(&buf);
 }
 
+static uint64_t perf_start_times[10];
+static int perf_indent;
+
+uint64_t trace_performance_enter(void)
+{
+	uint64_t now;
+
+	if (!trace_want(&trace_perf_key))
+		return 0;
+
+	now = getnanotime();
+	perf_start_times[perf_indent] = now;
+	if (perf_indent + 1 < ARRAY_SIZE(perf_start_times))
+		perf_indent++;
+	else
+		BUG("Too deep indentation");
+	return now;
+}
+
 static void trace_performance_vprintf_fl(const char *file, int line,
 					 uint64_t nanos, const char *format,
 					 va_list ap)
 {
+	static const char space[] = "          ";
 	struct strbuf buf = STRBUF_INIT;
 
 	if (!prepare_trace_line(file, line, &trace_perf_key, &buf))
@@ -188,7 +208,10 @@ static void trace_performance_vprintf_fl(const char *file, int line,
 	strbuf_addf(&buf, "performance: %.9f s", (double) nanos / 1000000000);
 
 	if (format && *format) {
-		strbuf_addstr(&buf, ": ");
+		if (perf_indent >= strlen(space))
+			BUG("Too deep indentation");
+
+		strbuf_addf(&buf, ":%.*s ", perf_indent, space);
 		strbuf_vaddf(&buf, format, ap);
 	}
 
@@ -244,6 +267,24 @@ void trace_performance_since(uint64_t start, const char *format, ...)
 	va_end(ap);
 }
 
+void trace_performance_leave(const char *format, ...)
+{
+	va_list ap;
+	uint64_t since;
+
+	if (perf_indent)
+		perf_indent--;
+
+	if (!format) /* Allow callers to leave without tracing anything */
+		return;
+
+	since = perf_start_times[perf_indent];
+	va_start(ap, format);
+	trace_performance_vprintf_fl(NULL, 0, getnanotime() - since,
+				     format, ap);
+	va_end(ap);
+}
+
 #else
 
 void trace_printf_key_fl(const char *file, int line, struct trace_key *key,
@@ -273,6 +314,24 @@ void trace_performance_fl(const char *file, int line, uint64_t nanos,
 	va_end(ap);
 }
 
+void trace_performance_leave_fl(const char *file, int line,
+				uint64_t nanos, const char *format, ...)
+{
+	va_list ap;
+	uint64_t since;
+
+	if (perf_indent)
+		perf_indent--;
+
+	if (!format) /* Allow callers to leave without tracing anything */
+		return;
+
+	since = perf_start_times[perf_indent];
+	va_start(ap, format);
+	trace_performance_vprintf_fl(file, line, nanos - since, format, ap);
+	va_end(ap);
+}
+
 #endif /* HAVE_VARIADIC_MACROS */
 
 
@@ -411,13 +470,11 @@ uint64_t getnanotime(void)
 	}
 }
 
-static uint64_t command_start_time;
 static struct strbuf command_line = STRBUF_INIT;
 
 static void print_command_performance_atexit(void)
 {
-	trace_performance_since(command_start_time, "git command:%s",
-				command_line.buf);
+	trace_performance_leave("git command:%s", command_line.buf);
 }
 
 void trace_command_performance(const char **argv)
@@ -425,10 +482,10 @@ void trace_command_performance(const char **argv)
 	if (!trace_want(&trace_perf_key))
 		return;
 
-	if (!command_start_time)
+	if (!command_line.len)
 		atexit(print_command_performance_atexit);
 
 	strbuf_reset(&command_line);
 	sq_quote_argv_pretty(&command_line, argv);
-	command_start_time = getnanotime();
+	trace_performance_enter();
 }
diff --git a/trace.h b/trace.h
index 2b6a1bc17c..171b256d26 100644
--- a/trace.h
+++ b/trace.h
@@ -23,6 +23,7 @@ extern void trace_disable(struct trace_key *key);
 extern uint64_t getnanotime(void);
 extern void trace_command_performance(const char **argv);
 extern void trace_verbatim(struct trace_key *key, const void *buf, unsigned len);
+uint64_t trace_performance_enter(void);
 
 #ifndef HAVE_VARIADIC_MACROS
 
@@ -45,6 +46,9 @@ extern void trace_performance(uint64_t nanos, const char *format, ...);
 __attribute__((format (printf, 2, 3)))
 extern void trace_performance_since(uint64_t start, const char *format, ...);
 
+__attribute__((format (printf, 1, 2)))
+void trace_performance_leave(const char *format, ...);
+
 #else
 
 /*
@@ -118,6 +122,14 @@ extern void trace_performance_since(uint64_t start, const char *format, ...);
 					     __VA_ARGS__);		    \
 	} while (0)
 
+#define trace_performance_leave(...)					    \
+	do {								    \
+		if (trace_pass_fl(&trace_perf_key))			    \
+			trace_performance_leave_fl(TRACE_CONTEXT, __LINE__, \
+						   getnanotime(),	    \
+						   __VA_ARGS__);	    \
+	} while (0)
+
 /* backend functions, use non-*fl macros instead */
 __attribute__((format (printf, 4, 5)))
 extern void trace_printf_key_fl(const char *file, int line, struct trace_key *key,
@@ -130,6 +142,9 @@ extern void trace_strbuf_fl(const char *file, int line, struct trace_key *key,
 __attribute__((format (printf, 4, 5)))
 extern void trace_performance_fl(const char *file, int line,
 				 uint64_t nanos, const char *fmt, ...);
+__attribute__((format (printf, 4, 5)))
+extern void trace_performance_leave_fl(const char *file, int line,
+				       uint64_t nanos, const char *fmt, ...);
 static inline int trace_pass_fl(struct trace_key *key)
 {
 	return key->fd || !key->initialized;
diff --git a/unpack-trees.c b/unpack-trees.c
index cfa88bb6ec..55f864ac57 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -385,6 +385,7 @@ static int check_updates(struct unpack_trees_options *o)
 	struct checkout state = CHECKOUT_INIT;
 	int i;
 
+	trace_performance_enter();
 	state.force = 1;
 	state.quiet = 1;
 	state.refresh_cache = 1;
@@ -461,6 +462,7 @@ static int check_updates(struct unpack_trees_options *o)
 	if (o->clone)
 		report_collided_checkout(index);
 
+	trace_performance_leave("check_updates");
 	return errs != 0;
 }
 
@@ -680,6 +682,113 @@ static inline int are_same_oid(struct name_entry *name_j, struct name_entry *nam
 	return name_j->oid && name_k->oid && !oidcmp(name_j->oid, name_k->oid);
 }
 
+static int all_trees_same_as_cache_tree(int n, unsigned long dirmask,
+					struct name_entry *names,
+					struct traverse_info *info)
+{
+	struct unpack_trees_options *o = info->data;
+	int i;
+
+	if (!o->merge || dirmask != ((1 << n) - 1))
+		return 0;
+
+	for (i = 1; i < n; i++)
+		if (!are_same_oid(names, names + i))
+			return 0;
+
+	return cache_tree_matches_traversal(o->src_index->cache_tree, names, info);
+}
+
+static int index_pos_by_traverse_info(struct name_entry *names,
+				      struct traverse_info *info)
+{
+	struct unpack_trees_options *o = info->data;
+	int len = traverse_path_len(info, names);
+	char *name = xmalloc(len + 1 /* slash */ + 1 /* NUL */);
+	int pos;
+
+	make_traverse_path(name, info, names);
+	name[len++] = '/';
+	name[len] = '\0';
+	pos = index_name_pos(o->src_index, name, len);
+	if (pos >= 0)
+		BUG("This is a directory and should not exist in index");
+	pos = -pos - 1;
+	if (!starts_with(o->src_index->cache[pos]->name, name) ||
+	    (pos > 0 && starts_with(o->src_index->cache[pos-1]->name, name)))
+		BUG("pos must point at the first entry in this directory");
+	free(name);
+	return pos;
+}
+
+/*
+ * Fast path if we detect that all trees are the same as cache-tree at this
+ * path. We'll walk these trees in an iterative loop using cache-tree/index
+ * instead of ODB since we already know what these trees contain.
+ */
+static int traverse_by_cache_tree(int pos, int nr_entries, int nr_names,
+				  struct name_entry *names,
+				  struct traverse_info *info)
+{
+	struct cache_entry *src[MAX_UNPACK_TREES + 1] = { NULL, };
+	struct unpack_trees_options *o = info->data;
+	struct cache_entry *tree_ce = NULL;
+	int ce_len = 0;
+	int i, d;
+
+	if (!o->merge)
+		BUG("We need cache-tree to do this optimization");
+
+	/*
+	 * Do what unpack_callback() and unpack_nondirectories() normally
+	 * do. But we walk all paths in an iterative loop instead.
+	 *
+	 * D/F conflicts and higher stage entries are not a concern
+	 * because cache-tree would be invalidated and we would never
+	 * get here in the first place.
+	 */
+	for (i = 0; i < nr_entries; i++) {
+		int new_ce_len, len, rc;
+
+		src[0] = o->src_index->cache[pos + i];
+
+		len = ce_namelen(src[0]);
+		new_ce_len = cache_entry_size(len);
+
+		if (new_ce_len > ce_len) {
+			new_ce_len <<= 1;
+			tree_ce = xrealloc(tree_ce, new_ce_len);
+			memset(tree_ce, 0, new_ce_len);
+			ce_len = new_ce_len;
+
+			tree_ce->ce_flags = create_ce_flags(0);
+
+			for (d = 1; d <= nr_names; d++)
+				src[d] = tree_ce;
+		}
+
+		tree_ce->ce_mode = src[0]->ce_mode;
+		tree_ce->ce_namelen = len;
+		oidcpy(&tree_ce->oid, &src[0]->oid);
+		memcpy(tree_ce->name, src[0]->name, len + 1);
+
+		rc = call_unpack_fn((const struct cache_entry * const *)src, o);
+		if (rc < 0) {
+			free(tree_ce);
+			return rc;
+		}
+
+		mark_ce_used(src[0], o);
+	}
+	free(tree_ce);
+	if (o->debug_unpack)
+		printf("Unpacked %d entries from %s to %s using cache-tree\n",
+		       nr_entries,
+		       o->src_index->cache[pos]->name,
+		       o->src_index->cache[pos + nr_entries - 1]->name);
+	return 0;
+}
+
 static int traverse_trees_recursive(int n, unsigned long dirmask,
 				    unsigned long df_conflicts,
 				    struct name_entry *names,
@@ -691,6 +800,27 @@ static int traverse_trees_recursive(int n, unsigned long dirmask,
 	void *buf[MAX_UNPACK_TREES];
 	struct traverse_info newinfo;
 	struct name_entry *p;
+	int nr_entries;
+
+	nr_entries = all_trees_same_as_cache_tree(n, dirmask, names, info);
+	if (nr_entries > 0) {
+		struct unpack_trees_options *o = info->data;
+		int pos = index_pos_by_traverse_info(names, info);
+
+		if (!o->merge || df_conflicts)
+			BUG("Wrong condition to get here buddy");
+
+		/*
+		 * All entries up to 'pos' must have been processed
+		 * (i.e. marked CE_UNPACKED) at this point. But to be safe,
+		 * save and restore cache_bottom anyway to not miss
+		 * unprocessed entries before 'pos'.
+		 */
+		bottom = o->cache_bottom;
+		ret = traverse_by_cache_tree(pos, nr_entries, n, names, info);
+		o->cache_bottom = bottom;
+		return ret;
+	}
 
 	p = names;
 	while (!p->mode)
@@ -857,6 +987,11 @@ static struct cache_entry *create_ce_entry(const struct traverse_info *info,
 	return ce;
 }
 
+/*
+ * Note that traverse_by_cache_tree() duplicates some logic in this function
+ * without actually calling it. If you change the logic here you may need to
+ * check and change there as well.
+ */
 static int unpack_nondirectories(int n, unsigned long mask,
 				 unsigned long dirmask,
 				 struct cache_entry **src,
@@ -1049,6 +1184,11 @@ static void debug_unpack_callback(int n,
 		debug_name_entry(i, names + i);
 }
 
+/*
+ * Note that traverse_by_cache_tree() duplicates some logic in this function
+ * without actually calling it. If you change the logic here you may need to
+ * check and change there as well.
+ */
 static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, struct name_entry *names, struct traverse_info *info)
 {
 	struct cache_entry *src[MAX_UNPACK_TREES + 1] = { NULL, };
@@ -1336,6 +1476,7 @@ 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);
 
+	trace_performance_enter();
 	memset(&el, 0, sizeof(el));
 	if (!core_apply_sparse_checkout || !o->update)
 		o->skip_sparse_checkout = 1;
@@ -1408,7 +1549,10 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 			}
 		}
 
-		if (traverse_trees(len, t, &info) < 0)
+		trace_performance_enter();
+		ret = traverse_trees(len, t, &info);
+		trace_performance_leave("traverse_trees");
+		if (ret < 0)
 			goto return_failed;
 	}
 
@@ -1483,7 +1627,10 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 
 	ret = check_updates(o) ? (-2) : 0;
 	if (o->dst_index) {
+		move_index_extensions(&o->result, o->src_index);
 		if (!ret) {
+			if (git_env_bool("GIT_TEST_CHECK_CACHE_TREE", 0))
+				cache_tree_verify(&o->result);
 			if (!o->result.cache_tree)
 				o->result.cache_tree = cache_tree();
 			if (!cache_tree_fully_valid(o->result.cache_tree))
@@ -1491,7 +1638,6 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 						  WRITE_TREE_SILENT |
 						  WRITE_TREE_REPAIR);
 		}
-		move_index_extensions(&o->result, o->src_index);
 		discard_index(o->dst_index);
 		*o->dst_index = o->result;
 	} else {
@@ -1500,6 +1646,7 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 	o->src_index = NULL;
 
 done:
+	trace_performance_leave("unpack_trees");
 	clear_exclude_list(&el);
 	return ret;
 
@@ -1691,6 +1838,7 @@ static int verify_clean_subdirectory(const struct cache_entry *ce,
 			if (verify_uptodate(ce2, o))
 				return -1;
 			add_entry(o, ce2, CE_REMOVE, 0);
+			invalidate_ce_path(ce, o);
 			mark_ce_used(ce2, o);
 		}
 		cnt++;
@@ -1950,6 +2098,8 @@ static int keep_entry(const struct cache_entry *ce,
 		      struct unpack_trees_options *o)
 {
 	add_entry(o, ce, 0, 0);
+	if (ce_stage(ce))
+		invalidate_ce_path(ce, o);
 	return 1;
 }