Merge branch 'jc/cache-tree'

* jc/cache-tree: (26 commits)
  builtin-rm: squelch compiler warnings.
  git-write-tree writes garbage on sparc64
  Fix crash when reading the empty tree
  fsck-objects: do not segfault on missing tree in cache-tree
  cache-tree: a bit more debugging support.
  read-tree: invalidate cache-tree entry when a new index entry is added.
  Fix test-dump-cache-tree in one-tree disappeared case.
  fsck-objects: mark objects reachable from cache-tree
  cache-tree: replace a sscanf() by two strtol() calls
  cache-tree.c: typefix
  test-dump-cache-tree: validate the cached data as well.
  cache_tree_update: give an option to update cache-tree only.
  read-tree: teach 1-way merege and plain read to prime cache-tree.
  read-tree: teach 1 and 2 way merges about cache-tree.
  update-index: when --unresolve, smudge the relevant cache-tree entries.
  test-dump-cache-tree: report number of subtrees.
  cache-tree: sort the subtree entries.
  Teach fsck-objects about cache-tree.
  index: make the index file format extensible.
  cache-tree: protect against "git prune".
  ...

Conflicts:

	Makefile, builtin.h, git.c: resolved the same way as in next.

15 files changed, 834 insertions, 128 deletions

diff --git a/.gitignore b/.gitignore
index ec4c0dc3d..afd087621 100644
--- a/.gitignore
+++ b/.gitignore
@@ -125,6 +125,7 @@ git-write-tree
 git-core-*/?*
 test-date
 test-delta
+test-dump-cache-tree
 common-cmds.h
 *.tar.gz
 *.dsc
diff --git a/Makefile b/Makefile
index 5ad16a0f4..b6fce394e 100644
--- a/Makefile
+++ b/Makefile
@@ -210,7 +210,7 @@ DIFF_OBJS = \
 	diffcore-delta.o log-tree.o
 
 LIB_OBJS = \
-	blob.o commit.o connect.o csum-file.o base85.o \
+	blob.o commit.o connect.o csum-file.o cache-tree.o base85.o \
 	date.o diff-delta.o entry.o exec_cmd.o ident.o index.o \
 	object.o pack-check.o patch-delta.o path.o pkt-line.o \
 	quote.o read-cache.o refs.o run-command.o dir.o \
@@ -626,6 +626,9 @@ test-date$X: test-date.c date.o ctype.o
 test-delta$X: test-delta.c diff-delta.o patch-delta.o
 	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $^
 
+test-dump-cache-tree$X: dump-cache-tree.o $(GITLIBS)
+	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
+
 check:
 	for i in *.c; do sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; done
 
diff --git a/builtin-add.c b/builtin-add.c
index 6166f66bc..02fe38b0c 100644
--- a/builtin-add.c
+++ b/builtin-add.c
@@ -8,6 +8,7 @@
 #include "cache.h"
 #include "builtin.h"
 #include "dir.h"
+#include "cache-tree.h"
 
 static const char builtin_add_usage[] =
 "git-add [-n] [-v] <filepattern>...";
@@ -117,6 +118,7 @@ static int add_file_to_index(const char *path, int verbose)
 		die("unable to add %s to index",path);
 	if (verbose)
 		printf("add '%s'\n", path);
+	cache_tree_invalidate_path(active_cache_tree, path);
 	return 0;
 }
 
diff --git a/builtin-apply.c b/builtin-apply.c
index 4056b9d67..f16c753be 100644
--- a/builtin-apply.c
+++ b/builtin-apply.c
@@ -8,6 +8,7 @@
  */
 #include <fnmatch.h>
 #include "cache.h"
+#include "cache-tree.h"
 #include "quote.h"
 #include "blob.h"
 #include "delta.h"
@@ -1918,6 +1919,7 @@ static void remove_file(struct patch *patch)
 	if (write_index) {
 		if (remove_file_from_cache(patch->old_name) < 0)
 			die("unable to remove %s from index", patch->old_name);
+		cache_tree_invalidate_path(active_cache_tree, patch->old_name);
 	}
 	if (!cached)
 		unlink(patch->old_name);
@@ -2019,8 +2021,9 @@ static void create_file(struct patch *patch)
 
 	if (!mode)
 		mode = S_IFREG | 0644;
-	create_one_file(path, mode, buf, size);	
+	create_one_file(path, mode, buf, size);
 	add_index_file(path, mode, buf, size);
+	cache_tree_invalidate_path(active_cache_tree, path);
 }
 
 static void write_out_one_result(struct patch *patch)
diff --git a/builtin-read-tree.c b/builtin-read-tree.c
index ec40d013c..716f79251 100644
--- a/builtin-read-tree.c
+++ b/builtin-read-tree.c
@@ -9,6 +9,7 @@
 
 #include "object.h"
 #include "tree.h"
+#include "cache-tree.h"
 #include <sys/time.h>
 #include <signal.h>
 #include "builtin.h"
@@ -427,6 +428,12 @@ static void verify_uptodate(struct cache_entry *ce)
 	die("Entry '%s' not uptodate. Cannot merge.", ce->name);
 }
 
+static void invalidate_ce_path(struct cache_entry *ce)
+{
+	if (ce)
+		cache_tree_invalidate_path(active_cache_tree, ce->name);
+}
+
 /*
  * We do not want to remove or overwrite a working tree file that
  * is not tracked.
@@ -457,10 +464,13 @@ static int merged_entry(struct cache_entry *merge, struct cache_entry *old)
 			*merge = *old;
 		} else {
 			verify_uptodate(old);
+			invalidate_ce_path(old);
 		}
 	}
-	else
+	else {
 		verify_absent(merge->name, "overwritten");
+		invalidate_ce_path(merge);
+	}
 
 	merge->ce_flags &= ~htons(CE_STAGEMASK);
 	add_cache_entry(merge, ADD_CACHE_OK_TO_ADD);
@@ -475,6 +485,7 @@ static int deleted_entry(struct cache_entry *ce, struct cache_entry *old)
 		verify_absent(ce->name, "removed");
 	ce->ce_mode = 0;
 	add_cache_entry(ce, ADD_CACHE_OK_TO_ADD);
+	invalidate_ce_path(ce);
 	return 1;
 }
 
@@ -750,6 +761,7 @@ static int read_cache_unmerged(void)
 		struct cache_entry *ce = active_cache[i];
 		if (ce_stage(ce)) {
 			deleted++;
+			invalidate_ce_path(ce);
 			continue;
 		}
 		if (deleted)
@@ -760,6 +772,39 @@ static int read_cache_unmerged(void)
 	return deleted;
 }
 
+static void prime_cache_tree_rec(struct cache_tree *it, struct tree *tree)
+{
+	struct tree_entry_list *ent;
+	int cnt;
+
+	memcpy(it->sha1, tree->object.sha1, 20);
+	for (cnt = 0, ent = tree->entries; ent; ent = ent->next) {
+		if (!ent->directory)
+			cnt++;
+		else {
+			struct cache_tree_sub *sub;
+			struct tree *subtree = (struct tree *)ent->item.tree;
+			if (!subtree->object.parsed)
+				parse_tree(subtree);
+			sub = cache_tree_sub(it, ent->name);
+			sub->cache_tree = cache_tree();
+			prime_cache_tree_rec(sub->cache_tree, subtree);
+			cnt += sub->cache_tree->entry_count;
+		}
+	}
+	it->entry_count = cnt;
+}
+
+static void prime_cache_tree(void)
+{
+	struct tree *tree = (struct tree *)trees->item;
+	if (!tree)
+		return;
+	active_cache_tree = cache_tree();
+	prime_cache_tree_rec(active_cache_tree, tree);
+
+}
+
 static const char read_tree_usage[] = "git-read-tree (<sha> | -m [--aggressive] [-u | -i] <sha1> [<sha2> [<sha3>]])";
 
 static struct cache_file cache_file;
@@ -861,10 +906,9 @@ int cmd_read_tree(int argc, const char **argv, char **envp)
 			fn = twoway_merge;
 			break;
 		case 3:
-			fn = threeway_merge;
-			break;
 		default:
 			fn = threeway_merge;
+			cache_tree_free(&active_cache_tree);
 			break;
 		}
 
@@ -875,6 +919,18 @@ int cmd_read_tree(int argc, const char **argv, char **envp)
 	}
 
 	unpack_trees(fn);
+
+	/*
+	 * When reading only one tree (either the most basic form,
+	 * "-m ent" or "--reset ent" form), we can obtain a fully
+	 * valid cache-tree because the index must match exactly
+	 * what came from the tree.
+	 */
+	if (trees && trees->item && (!merge || (stage == 2))) {
+		cache_tree_free(&active_cache_tree);
+		prime_cache_tree();
+	}
+
 	if (write_cache(newfd, active_cache, active_nr) ||
 	    commit_index_file(&cache_file))
 		die("unable to write new index file");
diff --git a/builtin-rm.c b/builtin-rm.c
index 9014c6155..e7793a20f 100644
--- a/builtin-rm.c
+++ b/builtin-rm.c
@@ -6,6 +6,7 @@
 #include "cache.h"
 #include "builtin.h"
 #include "dir.h"
+#include "cache-tree.h"
 
 static const char builtin_rm_usage[] =
 "git-rm [-n] [-v] [-f] <filepattern>...";
@@ -117,6 +118,7 @@ int cmd_rm(int argc, const char **argv, char **envp)
 
 		if (remove_file_from_cache(path))
 			die("git rm: unable to remove %s", path);
+		cache_tree_invalidate_path(active_cache_tree, path);
 	}
 
 	/*
diff --git a/cache-tree.c b/cache-tree.c
new file mode 100644
index 000000000..a880c97b3
--- /dev/null
+++ b/cache-tree.c
@@ -0,0 +1,531 @@
+#include "cache.h"
+#include "tree.h"
+#include "cache-tree.h"
+
+#define DEBUG 0
+
+struct cache_tree *cache_tree(void)
+{
+	struct cache_tree *it = xcalloc(1, sizeof(struct cache_tree));
+	it->entry_count = -1;
+	return it;
+}
+
+void cache_tree_free(struct cache_tree **it_p)
+{
+	int i;
+	struct cache_tree *it = *it_p;
+
+	if (!it)
+		return;
+	for (i = 0; i < it->subtree_nr; i++)
+		if (it->down[i])
+			cache_tree_free(&it->down[i]->cache_tree);
+	free(it->down);
+	free(it);
+	*it_p = NULL;
+}
+
+static int subtree_name_cmp(const char *one, int onelen,
+			    const char *two, int twolen)
+{
+	if (onelen < twolen)
+		return -1;
+	if (twolen < onelen)
+		return 1;
+	return memcmp(one, two, onelen);
+}
+
+static int subtree_pos(struct cache_tree *it, const char *path, int pathlen)
+{
+	struct cache_tree_sub **down = it->down;
+	int lo, hi;
+	lo = 0;
+	hi = it->subtree_nr;
+	while (lo < hi) {
+		int mi = (lo + hi) / 2;
+		struct cache_tree_sub *mdl = down[mi];
+		int cmp = subtree_name_cmp(path, pathlen,
+					   mdl->name, mdl->namelen);
+		if (!cmp)
+			return mi;
+		if (cmp < 0)
+			hi = mi;
+		else
+			lo = mi + 1;
+	}
+	return -lo-1;
+}
+
+static struct cache_tree_sub *find_subtree(struct cache_tree *it,
+					   const char *path,
+					   int pathlen,
+					   int create)
+{
+	struct cache_tree_sub *down;
+	int pos = subtree_pos(it, path, pathlen);
+	if (0 <= pos)
+		return it->down[pos];
+	if (!create)
+		return NULL;
+
+	pos = -pos-1;
+	if (it->subtree_alloc <= it->subtree_nr) {
+		it->subtree_alloc = alloc_nr(it->subtree_alloc);
+		it->down = xrealloc(it->down, it->subtree_alloc *
+				    sizeof(*it->down));
+	}
+	it->subtree_nr++;
+
+	down = xmalloc(sizeof(*down) + pathlen + 1);
+	down->cache_tree = NULL;
+	down->namelen = pathlen;
+	memcpy(down->name, path, pathlen);
+	down->name[pathlen] = 0;
+
+	if (pos < it->subtree_nr)
+		memmove(it->down + pos + 1,
+			it->down + pos,
+			sizeof(down) * (it->subtree_nr - pos - 1));
+	it->down[pos] = down;
+	return down;
+}
+
+struct cache_tree_sub *cache_tree_sub(struct cache_tree *it, const char *path)
+{
+	int pathlen = strlen(path);
+	return find_subtree(it, path, pathlen, 1);
+}
+
+void cache_tree_invalidate_path(struct cache_tree *it, const char *path)
+{
+	/* a/b/c
+	 * ==> invalidate self
+	 * ==> find "a", have it invalidate "b/c"
+	 * a
+	 * ==> invalidate self
+	 * ==> if "a" exists as a subtree, remove it.
+	 */
+	const char *slash;
+	int namelen;
+	struct cache_tree_sub *down;
+
+#if DEBUG
+	fprintf(stderr, "cache-tree invalidate <%s>\n", path);
+#endif
+
+	if (!it)
+		return;
+	slash = strchr(path, '/');
+	it->entry_count = -1;
+	if (!slash) {
+		int pos;
+		namelen = strlen(path);
+		pos = subtree_pos(it, path, namelen);
+		if (0 <= pos) {
+			cache_tree_free(&it->down[pos]->cache_tree);
+			free(it->down[pos]);
+			/* 0 1 2 3 4 5
+			 *       ^     ^subtree_nr = 6
+			 *       pos
+			 * move 4 and 5 up one place (2 entries)
+			 * 2 = 6 - 3 - 1 = subtree_nr - pos - 1
+			 */
+			memmove(it->down+pos, it->down+pos+1,
+				sizeof(struct cache_tree_sub *) *
+				(it->subtree_nr - pos - 1));
+			it->subtree_nr--;
+		}
+		return;
+	}
+	namelen = slash - path;
+	down = find_subtree(it, path, namelen, 0);
+	if (down)
+		cache_tree_invalidate_path(down->cache_tree, slash + 1);
+}
+
+static int verify_cache(struct cache_entry **cache,
+			int entries)
+{
+	int i, funny;
+
+	/* Verify that the tree is merged */
+	funny = 0;
+	for (i = 0; i < entries; i++) {
+		struct cache_entry *ce = cache[i];
+		if (ce_stage(ce)) {
+			if (10 < ++funny) {
+				fprintf(stderr, "...\n");
+				break;
+			}
+			fprintf(stderr, "%s: unmerged (%s)\n",
+				ce->name, sha1_to_hex(ce->sha1));
+		}
+	}
+	if (funny)
+		return -1;
+
+	/* Also verify that the cache does not have path and path/file
+	 * at the same time.  At this point we know the cache has only
+	 * stage 0 entries.
+	 */
+	funny = 0;
+	for (i = 0; i < entries - 1; i++) {
+		/* path/file always comes after path because of the way
+		 * the cache is sorted.  Also path can appear only once,
+		 * which means conflicting one would immediately follow.
+		 */
+		const char *this_name = cache[i]->name;
+		const char *next_name = cache[i+1]->name;
+		int this_len = strlen(this_name);
+		if (this_len < strlen(next_name) &&
+		    strncmp(this_name, next_name, this_len) == 0 &&
+		    next_name[this_len] == '/') {
+			if (10 < ++funny) {
+				fprintf(stderr, "...\n");
+				break;
+			}
+			fprintf(stderr, "You have both %s and %s\n",
+				this_name, next_name);
+		}
+	}
+	if (funny)
+		return -1;
+	return 0;
+}
+
+static void discard_unused_subtrees(struct cache_tree *it)
+{
+	struct cache_tree_sub **down = it->down;
+	int nr = it->subtree_nr;
+	int dst, src;
+	for (dst = src = 0; src < nr; src++) {
+		struct cache_tree_sub *s = down[src];
+		if (s->used)
+			down[dst++] = s;
+		else {
+			cache_tree_free(&s->cache_tree);
+			free(s);
+			it->subtree_nr--;
+		}
+	}
+}
+
+int cache_tree_fully_valid(struct cache_tree *it)
+{
+	int i;
+	if (!it)
+		return 0;
+	if (it->entry_count < 0 || !has_sha1_file(it->sha1))
+		return 0;
+	for (i = 0; i < it->subtree_nr; i++) {
+		if (!cache_tree_fully_valid(it->down[i]->cache_tree))
+			return 0;
+	}
+	return 1;
+}
+
+static int update_one(struct cache_tree *it,
+		      struct cache_entry **cache,
+		      int entries,
+		      const char *base,
+		      int baselen,
+		      int missing_ok,
+		      int dryrun)
+{
+	unsigned long size, offset;
+	char *buffer;
+	int i;
+
+	if (0 <= it->entry_count && has_sha1_file(it->sha1))
+		return it->entry_count;
+
+	/*
+	 * We first scan for subtrees and update them; we start by
+	 * marking existing subtrees -- the ones that are unmarked
+	 * should not be in the result.
+	 */
+	for (i = 0; i < it->subtree_nr; i++)
+		it->down[i]->used = 0;
+
+	/*
+	 * Find the subtrees and update them.
+	 */
+	for (i = 0; i < entries; i++) {
+		struct cache_entry *ce = cache[i];
+		struct cache_tree_sub *sub;
+		const char *path, *slash;
+		int pathlen, sublen, subcnt;
+
+		path = ce->name;
+		pathlen = ce_namelen(ce);
+		if (pathlen <= baselen || memcmp(base, path, baselen))
+			break; /* at the end of this level */
+
+		slash = strchr(path + baselen, '/');
+		if (!slash)
+			continue;
+		/*
+		 * a/bbb/c (base = a/, slash = /c)
+		 * ==>
+		 * path+baselen = bbb/c, sublen = 3
+		 */
+		sublen = slash - (path + baselen);
+		sub = find_subtree(it, path + baselen, sublen, 1);
+		if (!sub->cache_tree)
+			sub->cache_tree = cache_tree();
+		subcnt = update_one(sub->cache_tree,
+				    cache + i, entries - i,
+				    path,
+				    baselen + sublen + 1,
+				    missing_ok,
+				    dryrun);
+		i += subcnt - 1;
+		sub->used = 1;
+	}
+
+	discard_unused_subtrees(it);
+
+	/*
+	 * Then write out the tree object for this level.
+	 */
+	size = 8192;
+	buffer = xmalloc(size);
+	offset = 0;
+
+	for (i = 0; i < entries; i++) {
+		struct cache_entry *ce = cache[i];
+		struct cache_tree_sub *sub;
+		const char *path, *slash;
+		int pathlen, entlen;
+		const unsigned char *sha1;
+		unsigned mode;
+
+		path = ce->name;
+		pathlen = ce_namelen(ce);
+		if (pathlen <= baselen || memcmp(base, path, baselen))
+			break; /* at the end of this level */
+
+		slash = strchr(path + baselen, '/');
+		if (slash) {
+			entlen = slash - (path + baselen);
+			sub = find_subtree(it, path + baselen, entlen, 0);
+			if (!sub)
+				die("cache-tree.c: '%.*s' in '%s' not found",
+				    entlen, path + baselen, path);
+			i += sub->cache_tree->entry_count - 1;
+			sha1 = sub->cache_tree->sha1;
+			mode = S_IFDIR;
+		}
+		else {
+			sha1 = ce->sha1;
+			mode = ntohl(ce->ce_mode);
+			entlen = pathlen - baselen;
+		}
+		if (!missing_ok && !has_sha1_file(sha1))
+			return error("invalid object %s", sha1_to_hex(sha1));
+
+		if (!ce->ce_mode)
+			continue; /* entry being removed */
+
+		if (size < offset + entlen + 100) {
+			size = alloc_nr(offset + entlen + 100);
+			buffer = xrealloc(buffer, size);
+		}
+		offset += sprintf(buffer + offset,
+				  "%o %.*s", mode, entlen, path + baselen);
+		buffer[offset++] = 0;
+		memcpy(buffer + offset, sha1, 20);
+		offset += 20;
+
+#if DEBUG
+		fprintf(stderr, "cache-tree update-one %o %.*s\n",
+			mode, entlen, path + baselen);
+#endif
+	}
+
+	if (dryrun) {
+		unsigned char hdr[200];
+		int hdrlen;
+		write_sha1_file_prepare(buffer, offset, tree_type, it->sha1,
+					hdr, &hdrlen);
+	}
+	else
+		write_sha1_file(buffer, offset, tree_type, it->sha1);
+	free(buffer);
+	it->entry_count = i;
+#if DEBUG
+	fprintf(stderr, "cache-tree update-one (%d ent, %d subtree) %s\n",
+		it->entry_count, it->subtree_nr,
+		sha1_to_hex(it->sha1));
+#endif
+	return i;
+}
+
+int cache_tree_update(struct cache_tree *it,
+		      struct cache_entry **cache,
+		      int entries,
+		      int missing_ok,
+		      int dryrun)
+{
+	int i;
+	i = verify_cache(cache, entries);
+	if (i)
+		return i;
+	i = update_one(it, cache, entries, "", 0, missing_ok, dryrun);
+	if (i < 0)
+		return i;
+	return 0;
+}
+
+static void *write_one(struct cache_tree *it,
+		       char *path,
+		       int pathlen,
+		       char *buffer,
+		       unsigned long *size,
+		       unsigned long *offset)
+{
+	int i;
+
+	/* One "cache-tree" entry consists of the following:
+	 * path (NUL terminated)
+	 * entry_count, subtree_nr ("%d %d\n")
+	 * tree-sha1 (missing if invalid)
+	 * subtree_nr "cache-tree" entries for subtrees.
+	 */
+	if (*size < *offset + pathlen + 100) {
+		*size = alloc_nr(*offset + pathlen + 100);
+		buffer = xrealloc(buffer, *size);
+	}
+	*offset += sprintf(buffer + *offset, "%.*s%c%d %d\n",
+			   pathlen, path, 0,
+			   it->entry_count, it->subtree_nr);
+
+#if DEBUG
+	if (0 <= it->entry_count)
+		fprintf(stderr, "cache-tree <%.*s> (%d ent, %d subtree) %s\n",
+			pathlen, path, it->entry_count, it->subtree_nr,
+			sha1_to_hex(it->sha1));
+	else
+		fprintf(stderr, "cache-tree <%.*s> (%d subtree) invalid\n",
+			pathlen, path, it->subtree_nr);
+#endif
+
+	if (0 <= it->entry_count) {
+		memcpy(buffer + *offset, it->sha1, 20);
+		*offset += 20;
+	}
+	for (i = 0; i < it->subtree_nr; i++) {
+		struct cache_tree_sub *down = it->down[i];
+		if (i) {
+			struct cache_tree_sub *prev = it->down[i-1];
+			if (subtree_name_cmp(down->name, down->namelen,
+					     prev->name, prev->namelen) <= 0)
+				die("fatal - unsorted cache subtree");
+		}
+		buffer = write_one(down->cache_tree, down->name, down->namelen,
+				   buffer, size, offset);
+	}
+	return buffer;
+}
+
+void *cache_tree_write(struct cache_tree *root, unsigned long *size_p)
+{
+	char path[PATH_MAX];
+	unsigned long size = 8192;
+	char *buffer = xmalloc(size);
+
+	*size_p = 0;
+	path[0] = 0;
+	return write_one(root, path, 0, buffer, &size, size_p);
+}
+
+static struct cache_tree *read_one(const char **buffer, unsigned long *size_p)
+{
+	const char *buf = *buffer;
+	unsigned long size = *size_p;
+	const char *cp;
+	char *ep;
+	struct cache_tree *it;
+	int i, subtree_nr;
+
+	it = NULL;
+	/* skip name, but make sure name exists */
+	while (size && *buf) {
+		size--;
+		buf++;
+	}
+	if (!size)
+		goto free_return;
+	buf++; size--;
+	it = cache_tree();
+
+	cp = buf;
+	it->entry_count = strtol(cp, &ep, 10);
+	if (cp == ep)
+		goto free_return;
+	cp = ep;
+	subtree_nr = strtol(cp, &ep, 10);
+	if (cp == ep)
+		goto free_return;
+	while (size && *buf && *buf != '\n') {
+		size--;
+		buf++;
+	}
+	if (!size)
+		goto free_return;
+	buf++; size--;
+	if (0 <= it->entry_count) {
+		if (size < 20)
+			goto free_return;
+		memcpy(it->sha1, buf, 20);
+		buf += 20;
+		size -= 20;
+	}
+
+#if DEBUG
+	if (0 <= it->entry_count)
+		fprintf(stderr, "cache-tree <%s> (%d ent, %d subtree) %s\n",
+			*buffer, it->entry_count, subtree_nr,
+			sha1_to_hex(it->sha1));
+	else
+		fprintf(stderr, "cache-tree <%s> (%d subtrees) invalid\n",
+			*buffer, subtree_nr);
+#endif
+
+	/*
+	 * Just a heuristic -- we do not add directories that often but
+	 * we do not want to have to extend it immediately when we do,
+	 * hence +2.
+	 */
+	it->subtree_alloc = subtree_nr + 2;
+	it->down = xcalloc(it->subtree_alloc, sizeof(struct cache_tree_sub *));
+	for (i = 0; i < subtree_nr; i++) {
+		/* read each subtree */
+		struct cache_tree *sub;
+		struct cache_tree_sub *subtree;
+		const char *name = buf;
+
+		sub = read_one(&buf, &size);
+		if (!sub)
+			goto free_return;
+		subtree = cache_tree_sub(it, name);
+		subtree->cache_tree = sub;
+	}
+	if (subtree_nr != it->subtree_nr)
+		die("cache-tree: internal error");
+	*buffer = buf;
+	*size_p = size;
+	return it;
+
+ free_return:
+	cache_tree_free(&it);
+	return NULL;
+}
+
+struct cache_tree *cache_tree_read(const char *buffer, unsigned long size)
+{
+	if (buffer[0])
+		return NULL; /* not the whole tree */
+	return read_one(&buffer, &size);
+}
diff --git a/cache-tree.h b/cache-tree.h
new file mode 100644
index 000000000..72c64801f
--- /dev/null
+++ b/cache-tree.h
@@ -0,0 +1,31 @@
+#ifndef CACHE_TREE_H
+#define CACHE_TREE_H
+
+struct cache_tree;
+struct cache_tree_sub {
+	struct cache_tree *cache_tree;
+	int namelen;
+	int used;
+	char name[FLEX_ARRAY];
+};
+
+struct cache_tree {
+	int entry_count; /* negative means "invalid" */
+	unsigned char sha1[20];
+	int subtree_nr;
+	int subtree_alloc;
+	struct cache_tree_sub **down;
+};
+
+struct cache_tree *cache_tree(void);
+void cache_tree_free(struct cache_tree **);
+void cache_tree_invalidate_path(struct cache_tree *, const char *);
+struct cache_tree_sub *cache_tree_sub(struct cache_tree *, const char *);
+
+void *cache_tree_write(struct cache_tree *root, unsigned long *size_p);
+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 cache_tree *, struct cache_entry **, int, int, int);
+
+#endif
diff --git a/cache.h b/cache.h
index 3a46fb97b..f11d5e7dc 100644
--- a/cache.h
+++ b/cache.h
@@ -114,6 +114,7 @@ static inline unsigned int create_ce_mode(unsigned int mode)
 
 extern struct cache_entry **active_cache;
 extern unsigned int active_nr, active_alloc, active_cache_changed;
+extern struct cache_tree *active_cache_tree;
 
 #define GIT_DIR_ENVIRONMENT "GIT_DIR"
 #define DEFAULT_GIT_DIR_ENVIRONMENT ".git"
diff --git a/checkout-index.c b/checkout-index.c
index cc3a745c1..9876af6fd 100644
--- a/checkout-index.c
+++ b/checkout-index.c
@@ -39,6 +39,7 @@
 #include "cache.h"
 #include "strbuf.h"
 #include "quote.h"
+#include "cache-tree.h"
 
 #define CHECKOUT_ALL 4
 static const char *prefix;
diff --git a/dump-cache-tree.c b/dump-cache-tree.c
new file mode 100644
index 000000000..1ccaf5177
--- /dev/null
+++ b/dump-cache-tree.c
@@ -0,0 +1,64 @@
+#include "cache.h"
+#include "tree.h"
+#include "cache-tree.h"
+
+
+static void dump_one(struct cache_tree *it, const char *pfx, const char *x)
+{
+	if (it->entry_count < 0)
+		printf("%-40s %s%s (%d subtrees)\n",
+		       "invalid", x, pfx, it->subtree_nr);
+	else
+		printf("%s %s%s (%d entries, %d subtrees)\n",
+		       sha1_to_hex(it->sha1), x, pfx,
+		       it->entry_count, it->subtree_nr);
+}
+
+static int dump_cache_tree(struct cache_tree *it,
+			   struct cache_tree *ref,
+			   const char *pfx)
+{
+	int i;
+	int errs = 0;
+
+	if (!it || !ref)
+		/* missing in either */
+		return 0;
+
+	if (it->entry_count < 0) {
+		dump_one(it, pfx, "");
+		dump_one(ref, pfx, "#(ref) ");
+		if (it->subtree_nr != ref->subtree_nr)
+			errs = 1;
+	}
+	else {
+		dump_one(it, pfx, "");
+		if (memcmp(it->sha1, ref->sha1, 20) ||
+		    ref->entry_count != it->entry_count ||
+		    ref->subtree_nr != it->subtree_nr) {
+			dump_one(ref, pfx, "#(ref) ");
+			errs = 1;
+		}
+	}
+
+	for (i = 0; i < it->subtree_nr; i++) {
+		char path[PATH_MAX];
+		struct cache_tree_sub *down = it->down[i];
+		struct cache_tree_sub *rdwn;
+
+		rdwn = cache_tree_sub(ref, down->name);
+		sprintf(path, "%s%.*s/", pfx, down->namelen, down->name);
+		if (dump_cache_tree(down->cache_tree, rdwn->cache_tree, path))
+			errs = 1;
+	}
+	return errs;
+}
+
+int main(int ac, char **av)
+{
+	struct cache_tree *another = cache_tree();
+	if (read_cache() < 0)
+		die("unable to read index file");
+	cache_tree_update(another, active_cache, active_nr, 0, 1);
+	return dump_cache_tree(active_cache_tree, another, "");
+}
diff --git a/fsck-objects.c b/fsck-objects.c
index 59b25904c..1922b6d84 100644
--- a/fsck-objects.c
+++ b/fsck-objects.c
@@ -8,6 +8,7 @@
 #include "tag.h"
 #include "refs.h"
 #include "pack.h"
+#include "cache-tree.h"
 
 #define REACHABLE 0x0001
 
@@ -438,6 +439,28 @@ static int fsck_head_link(void)
 	return 0;
 }
 
+static int fsck_cache_tree(struct cache_tree *it)
+{
+	int i;
+	int err = 0;
+
+	if (0 <= it->entry_count) {
+		struct object *obj = parse_object(it->sha1);
+		if (!obj) {
+			error("%s: invalid sha1 pointer in cache-tree",
+			      sha1_to_hex(it->sha1));
+			return 1;
+		}
+		mark_reachable(obj, REACHABLE);
+		obj->used = 1;
+		if (obj->type != tree_type)
+			err |= objerror(obj, "non-tree in cache-tree");
+	}
+	for (i = 0; i < it->subtree_nr; i++)
+		err |= fsck_cache_tree(it->down[i]->cache_tree);
+	return err;
+}
+
 int main(int argc, char **argv)
 {
 	int i, heads;
@@ -547,6 +570,8 @@ int main(int argc, char **argv)
 			obj->used = 1;
 			mark_reachable(obj, REACHABLE);
 		}
+		if (active_cache_tree)
+			fsck_cache_tree(active_cache_tree);
 	}
 
 	check_connectivity();
diff --git a/read-cache.c b/read-cache.c
index 32ba91792..c499c5185 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -4,11 +4,26 @@
  * Copyright (C) Linus Torvalds, 2005
  */
 #include "cache.h"
+#include "cache-tree.h"
+
+/* Index extensions.
+ *
+ * The first letter should be 'A'..'Z' for extensions that are not
+ * necessary for a correct operation (i.e. optimization data).
+ * When new extensions are added that _needs_ to be understood in
+ * order to correctly interpret the index file, pick character that
+ * is outside the range, to cause the reader to abort.
+ */
+
+#define CACHE_EXT(s) ( (s[0]<<24)|(s[1]<<16)|(s[2]<<8)|(s[3]) )
+#define CACHE_EXT_TREE 0x54524545	/* "TREE" */
 
 struct cache_entry **active_cache = NULL;
 static time_t index_file_timestamp;
 unsigned int active_nr = 0, active_alloc = 0, active_cache_changed = 0;
 
+struct cache_tree *active_cache_tree = NULL;
+
 /*
  * This only updates the "non-critical" parts of the directory
  * cache, ie the parts that aren't tracked by GIT, and only used
@@ -696,6 +711,22 @@ static int verify_hdr(struct cache_header *hdr, unsigned long size)
 	return 0;
 }
 
+static int read_index_extension(const char *ext, void *data, unsigned long sz)
+{
+	switch (CACHE_EXT(ext)) {
+	case CACHE_EXT_TREE:
+		active_cache_tree = cache_tree_read(data, sz);
+		break;
+	default:
+		if (*ext < 'A' || 'Z' < *ext)
+			return error("index uses %.4s extension, which we do not understand",
+				     ext);
+		fprintf(stderr, "ignoring %.4s extension\n", ext);
+		break;
+	}
+	return 0;
+}
+
 int read_cache(void)
 {
 	int fd, i;
@@ -744,6 +775,22 @@ int read_cache(void)
 		active_cache[i] = ce;
 	}
 	index_file_timestamp = st.st_mtime;
+	while (offset <= size - 20 - 8) {
+		/* After an array of active_nr index entries,
+		 * there can be arbitrary number of extended
+		 * sections, each of which is prefixed with
+		 * extension name (4-byte) and section length
+		 * in 4-byte network byte order.
+		 */
+		unsigned long extsize;
+		memcpy(&extsize, map + offset + 4, 4);
+		extsize = ntohl(extsize);
+		if (read_index_extension(map + offset,
+					 map + offset + 8, extsize) < 0)
+			goto unmap;
+		offset += 8;
+		offset += extsize;
+	}
 	return active_nr;
 
 unmap:
@@ -778,6 +825,17 @@ static int ce_write(SHA_CTX *context, int fd, void *data, unsigned int len)
  	return 0;
 }
 
+static int write_index_ext_header(SHA_CTX *context, int fd,
+				  unsigned int ext, unsigned int sz)
+{
+	ext = htonl(ext);
+	sz = htonl(sz);
+	if ((ce_write(context, fd, &ext, 4) < 0) ||
+	    (ce_write(context, fd, &sz, 4) < 0))
+		return -1;
+	return 0;
+}
+
 static int ce_flush(SHA_CTX *context, int fd)
 {
 	unsigned int left = write_buffer_len;
@@ -874,5 +932,19 @@ int write_cache(int newfd, struct cache_entry **cache, int entries)
 		if (ce_write(&c, newfd, ce, ce_size(ce)) < 0)
 			return -1;
 	}
+
+	/* Write extension data here */
+	if (active_cache_tree) {
+		unsigned long sz;
+		void *data = cache_tree_write(active_cache_tree, &sz);
+		if (data &&
+		    !write_index_ext_header(&c, newfd, CACHE_EXT_TREE, sz) &&
+		    !ce_write(&c, newfd, data, sz))
+			;
+		else {
+			free(data);
+			return -1;
+		}
+	}
 	return ce_flush(&c, newfd);
 }
diff --git a/update-index.c b/update-index.c
index 5854d11fd..956b6b34f 100644
--- a/update-index.c
+++ b/update-index.c
@@ -6,6 +6,7 @@
 #include "cache.h"
 #include "strbuf.h"
 #include "quote.h"
+#include "cache-tree.h"
 #include "tree-walk.h"
 
 /*
@@ -51,6 +52,7 @@ static int mark_valid(const char *path)
 			active_cache[pos]->ce_flags &= ~htons(CE_VALID);
 			break;
 		}
+		cache_tree_invalidate_path(active_cache_tree, path);
 		active_cache_changed = 1;
 		return 0;
 	}
@@ -64,6 +66,12 @@ static int add_file_to_cache(const char *path)
 	struct stat st;
 
 	status = lstat(path, &st);
+
+	/* We probably want to do this in remove_file_from_cache() and
+	 * add_cache_entry() instead...
+	 */
+	cache_tree_invalidate_path(active_cache_tree, path);
+
 	if (status < 0 || S_ISDIR(st.st_mode)) {
 		/* When we used to have "path" and now we want to add
 		 * "path/file", we need a way to remove "path" before
@@ -145,6 +153,7 @@ static int add_cacheinfo(unsigned int mode, const unsigned char *sha1,
 		return error("%s: cannot add to the index - missing --add option?",
 			     path);
 	report("add '%s'", path);
+	cache_tree_invalidate_path(active_cache_tree, path);
 	return 0;
 }
 
@@ -169,6 +178,7 @@ static void chmod_path(int flip, const char *path)
 	default:
 		goto fail;
 	}
+	cache_tree_invalidate_path(active_cache_tree, path);
 	active_cache_changed = 1;
 	report("chmod %cx '%s'", flip, path);
 	return;
@@ -190,6 +200,7 @@ static void update_one(const char *path, const char *prefix, int prefix_length)
 			die("Unable to mark file %s", path);
 		goto free_return;
 	}
+	cache_tree_invalidate_path(active_cache_tree, path);
 
 	if (force_remove) {
 		if (remove_file_from_cache(p))
@@ -268,6 +279,7 @@ static void read_index_info(int line_termination)
 				free(path_name);
 			continue;
 		}
+		cache_tree_invalidate_path(active_cache_tree, path_name);
 
 		if (!mode) {
 			/* mode == 0 means there is no such path -- remove */
@@ -374,6 +386,7 @@ static int unresolve_one(const char *path)
 		goto free_return;
 	}
 
+	cache_tree_invalidate_path(active_cache_tree, path);
 	remove_file_from_cache(path);
 	if (add_cache_entry(ce_2, ADD_CACHE_OK_TO_ADD)) {
 		error("%s: cannot add our version to the index.", path);
diff --git a/write-tree.c b/write-tree.c
index dcad6e667..7a4f691d8 100644
--- a/write-tree.c
+++ b/write-tree.c
@@ -5,95 +5,21 @@
  */
 #include "cache.h"
 #include "tree.h"
+#include "cache-tree.h"
 
 static int missing_ok = 0;
 
-static int check_valid_sha1(unsigned char *sha1)
-{
-	int ret;
-
-	/* If we were anal, we'd check that the sha1 of the contents actually matches */
-	ret = has_sha1_file(sha1);
-	if (ret == 0)
-		perror(sha1_file_name(sha1));
-	return ret ? 0 : -1;
-}
-
-static int write_tree(struct cache_entry **cachep, int maxentries, const char *base, int baselen, unsigned char *returnsha1)
-{
-	unsigned char subdir_sha1[20];
-	unsigned long size, offset;
-	char *buffer;
-	int nr;
-
-	/* Guess at some random initial size */
-	size = 8192;
-	buffer = xmalloc(size);
-	offset = 0;
-
-	nr = 0;
-	while (nr < maxentries) {
-		struct cache_entry *ce = cachep[nr];
-		const char *pathname = ce->name, *filename, *dirname;
-		int pathlen = ce_namelen(ce), entrylen;
-		unsigned char *sha1;
-		unsigned int mode;
-
-		/* Did we hit the end of the directory? Return how many we wrote */
-		if (baselen >= pathlen || memcmp(base, pathname, baselen))
-			break;
-
-		sha1 = ce->sha1;
-		mode = ntohl(ce->ce_mode);
-
-		/* Do we have _further_ subdirectories? */
-		filename = pathname + baselen;
-		dirname = strchr(filename, '/');
-		if (dirname) {
-			int subdir_written;
-
-			subdir_written = write_tree(cachep + nr, maxentries - nr, pathname, dirname-pathname+1, subdir_sha1);
-			nr += subdir_written;
-
-			/* Now we need to write out the directory entry into this tree.. */
-			mode = S_IFDIR;
-			pathlen = dirname - pathname;
-
-			/* ..but the directory entry doesn't count towards the total count */
-			nr--;
-			sha1 = subdir_sha1;
-		}
-
-		if (!missing_ok && check_valid_sha1(sha1) < 0)
-			exit(1);
-
-		entrylen = pathlen - baselen;
-		if (offset + entrylen + 100 > size) {
-			size = alloc_nr(offset + entrylen + 100);
-			buffer = xrealloc(buffer, size);
-		}
-		offset += sprintf(buffer + offset, "%o %.*s", mode, entrylen, filename);
-		buffer[offset++] = 0;
-		memcpy(buffer + offset, sha1, 20);
-		offset += 20;
-		nr++;
-	}
-
-	write_sha1_file(buffer, offset, tree_type, returnsha1);
-	free(buffer);
-	return nr;
-}
-
 static const char write_tree_usage[] = "git-write-tree [--missing-ok]";
 
+static struct cache_file cache_file;
+
 int main(int argc, char **argv)
 {
-	int i, funny;
-	int entries;
-	unsigned char sha1[20];
-	
+	int entries, was_valid, newfd;
+
 	setup_git_directory();
 
+	newfd = hold_index_file_for_update(&cache_file, get_index_file());
 	entries = read_cache();
 	if (argc == 2) {
 		if (!strcmp(argv[1], "--missing-ok"))
@@ -108,51 +34,26 @@ int main(int argc, char **argv)
 	if (entries < 0)
 		die("git-write-tree: error reading cache");
 
-	/* Verify that the tree is merged */
-	funny = 0;
-	for (i = 0; i < entries; i++) {
-		struct cache_entry *ce = active_cache[i];
-		if (ce_stage(ce)) {
-			if (10 < ++funny) {
-				fprintf(stderr, "...\n");
-				break;
-			}
-			fprintf(stderr, "%s: unmerged (%s)\n", ce->name, sha1_to_hex(ce->sha1));
+	if (!active_cache_tree)
+		active_cache_tree = cache_tree();
+
+	was_valid = cache_tree_fully_valid(active_cache_tree);
+	if (!was_valid) {
+		if (cache_tree_update(active_cache_tree,
+				      active_cache, active_nr,
+				      missing_ok, 0) < 0)
+			die("git-write-tree: error building trees");
+		if (0 <= newfd) {
+			if (!write_cache(newfd, active_cache, active_nr))
+				commit_index_file(&cache_file);
 		}
-	}
-	if (funny)
-		die("git-write-tree: not able to write tree");
-
-	/* Also verify that the cache does not have path and path/file
-	 * at the same time.  At this point we know the cache has only
-	 * stage 0 entries.
-	 */
-	funny = 0;
-	for (i = 0; i < entries - 1; i++) {
-		/* path/file always comes after path because of the way
-		 * the cache is sorted.  Also path can appear only once,
-		 * which means conflicting one would immediately follow.
+		/* Not being able to write is fine -- we are only interested
+		 * in updating the cache-tree part, and if the next caller
+		 * ends up using the old index with unupdated cache-tree part
+		 * it misses the work we did here, but that is just a
+		 * performance penalty and not a big deal.
 		 */
-		const char *this_name = active_cache[i]->name;
-		const char *next_name = active_cache[i+1]->name;
-		int this_len = strlen(this_name);
-		if (this_len < strlen(next_name) &&
-		    strncmp(this_name, next_name, this_len) == 0 &&
-		    next_name[this_len] == '/') {
-			if (10 < ++funny) {
-				fprintf(stderr, "...\n");
-				break;
-			}
-			fprintf(stderr, "You have both %s and %s\n",
-				this_name, next_name);
-		}
 	}
-	if (funny)
-		die("git-write-tree: not able to write tree");
-
-	/* Ok, write it out */
-	if (write_tree(active_cache, entries, "", 0, sha1) != entries)
-		die("git-write-tree: internal error");
-	printf("%s\n", sha1_to_hex(sha1));
+	printf("%s\n", sha1_to_hex(active_cache_tree->sha1));
 	return 0;
 }