From: Junio C Hamano <junkio@cox.net>
Date: Sat, 11 Mar 2006 07:02:23 +0000 (-0800)
Subject: Merge branch 'nh/http' into next
X-Git-Tag: v1.3.0-rc1~37
X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/c827a84c694f95a9c2e179192d34c33eccdbb10a?hp=1a703cba6dac85936a5026587a90dcb827d00088

Merge branch 'nh/http' into next

* nh/http:
http-push: cleanup
http-push: support for updating remote info/refs
http-push: improve remote lock management
http-push: refactor remote file/directory processing
HTTP slot reuse fixes
http-push: fix revision walk
---

diff --git a/Documentation/git-fsck-objects.txt b/Documentation/git-fsck-objects.txt
index 387b435484..93ce9dcc92 100644
--- a/Documentation/git-fsck-objects.txt
+++ b/Documentation/git-fsck-objects.txt
@@ -10,7 +10,7 @@ SYNOPSIS
 --------
 [verse]
 'git-fsck-objects' [--tags] [--root] [--unreachable] [--cache]
-		 [--standalone | --full] [--strict] [<object>*]
+		 [--full] [--strict] [<object>*]
 
 DESCRIPTION
 -----------
@@ -38,21 +38,14 @@ index file and all SHA1 references in .git/refs/* as heads.
 	Consider any object recorded in the index also as a head node for
 	an unreachability trace.
 
---standalone::
-	Limit checks to the contents of GIT_OBJECT_DIRECTORY
-	($GIT_DIR/objects), making sure that it is consistent and
-	complete without referring to objects found in alternate
-	object pools listed in GIT_ALTERNATE_OBJECT_DIRECTORIES,
-	nor packed git archives found in $GIT_DIR/objects/pack;
-	cannot be used with --full.
-
 --full::
 	Check not just objects in GIT_OBJECT_DIRECTORY
 	($GIT_DIR/objects), but also the ones found in alternate
-	object pools listed in GIT_ALTERNATE_OBJECT_DIRECTORIES,
+	object pools listed in GIT_ALTERNATE_OBJECT_DIRECTORIES
+	or $GIT_DIR/objects/info/alternates,
 	and in packed git archives found in $GIT_DIR/objects/pack
 	and corresponding pack subdirectories in alternate
-	object pools; cannot be used with --standalone.
+	object pools.
 
 --strict::
 	Enable more strict checking, namely to catch a file mode
diff --git a/Makefile b/Makefile
index 8a20c76e9e..0bdf03b7de 100644
--- a/Makefile
+++ b/Makefile
@@ -190,7 +190,7 @@ PYMODULES = \
 LIB_FILE=libgit.a
 
 LIB_H = \
-	blob.h cache.h commit.h count-delta.h csum-file.h delta.h \
+	blob.h cache.h commit.h csum-file.h delta.h \
 	diff.h object.h pack.h pkt-line.h quote.h refs.h \
 	run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h
 
@@ -200,7 +200,7 @@ DIFF_OBJS = \
 	diffcore-delta.o
 
 LIB_OBJS = \
-	blob.o commit.o connect.o count-delta.o csum-file.o \
+	blob.o commit.o connect.o csum-file.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 \
diff --git a/blame.c b/blame.c
index 90338af31c..1fb507028b 100644
--- a/blame.c
+++ b/blame.c
@@ -14,6 +14,7 @@
 #include "tree.h"
 #include "blob.h"
 #include "diff.h"
+#include "diffcore.h"
 #include "revision.h"
 
 #define DEBUG 0
@@ -34,7 +35,9 @@ struct util_info {
 	char *buf;
 	unsigned long size;
 	int num_lines;
-//    const char* path;
+	const char* pathname;
+
+	void* topo_data;
 };
 
 struct chunk {
@@ -342,25 +345,34 @@ static int map_line(struct commit *commit, int line)
 	return info->line_map[line];
 }
 
-static int fill_util_info(struct commit *commit, const char *path)
+static struct util_info* get_util(struct commit *commit)
 {
-	struct util_info *util;
-	if (commit->object.util)
-		return 0;
+	struct util_info *util = commit->object.util;
+
+	if (util)
+		return util;
 
 	util = xmalloc(sizeof(struct util_info));
+	util->buf = NULL;
+	util->size = 0;
+	util->line_map = NULL;
+	util->num_lines = -1;
+	util->pathname = NULL;
+	commit->object.util = util;
+	return util;
+}
+
+static int fill_util_info(struct commit *commit)
+{
+	struct util_info *util = commit->object.util;
+
+	assert(util);
+	assert(util->pathname);
 
-	if (get_blob_sha1(commit->tree, path, util->sha1)) {
-		free(util);
+	if (get_blob_sha1(commit->tree, util->pathname, util->sha1))
 		return 1;
-	} else {
-		util->buf = NULL;
-		util->size = 0;
-		util->line_map = NULL;
-		util->num_lines = -1;
-		commit->object.util = util;
+	else
 		return 0;
-	}
 }
 
 static void alloc_line_map(struct commit *commit)
@@ -389,10 +401,11 @@ static void alloc_line_map(struct commit *commit)
 
 static void init_first_commit(struct commit* commit, const char* filename)
 {
-	struct util_info* util;
+	struct util_info* util = commit->object.util;
 	int i;
 
-	if (fill_util_info(commit, filename))
+	util->pathname = filename;
+	if (fill_util_info(commit))
 		die("fill_util_info failed");
 
 	alloc_line_map(commit);
@@ -453,7 +466,7 @@ static void process_commits(struct rev_info *rev, const char *path,
 		if(num_parents == 0)
 			*initial = commit;
 
-		if(fill_util_info(commit, path))
+		if (fill_util_info(commit))
 			continue;
 
 		alloc_line_map(commit);
@@ -471,7 +484,7 @@ static void process_commits(struct rev_info *rev, const char *path,
 				printf("parent: %s\n",
 				       sha1_to_hex(parent->object.sha1));
 
-			if(fill_util_info(parent, path)) {
+			if (fill_util_info(parent)) {
 				num_parents--;
 				continue;
 			}
@@ -511,6 +524,135 @@ static void process_commits(struct rev_info *rev, const char *path,
 	} while ((commit = get_revision(rev)) != NULL);
 }
 
+
+static int compare_tree_path(struct rev_info* revs,
+			     struct commit* c1, struct commit* c2)
+{
+	const char* paths[2];
+	struct util_info* util = c2->object.util;
+	paths[0] = util->pathname;
+	paths[1] = NULL;
+
+	diff_tree_setup_paths(get_pathspec(revs->prefix, paths));
+	return rev_compare_tree(c1->tree, c2->tree);
+}
+
+
+static int same_tree_as_empty_path(struct rev_info *revs, struct tree* t1,
+				   const char* path)
+{
+	const char* paths[2];
+	paths[0] = path;
+	paths[1] = NULL;
+
+	diff_tree_setup_paths(get_pathspec(revs->prefix, paths));
+	return rev_same_tree_as_empty(t1);
+}
+
+static const char* find_rename(struct commit* commit, struct commit* parent)
+{
+	struct util_info* cutil = commit->object.util;
+	struct diff_options diff_opts;
+	const char *paths[1];
+	int i;
+
+	if (DEBUG) {
+		printf("find_rename commit: %s ",
+		       sha1_to_hex(commit->object.sha1));
+		puts(sha1_to_hex(parent->object.sha1));
+	}
+
+	diff_setup(&diff_opts);
+	diff_opts.recursive = 1;
+	diff_opts.detect_rename = DIFF_DETECT_RENAME;
+	paths[0] = NULL;
+	diff_tree_setup_paths(paths);
+	if (diff_setup_done(&diff_opts) < 0)
+		die("diff_setup_done failed");
+
+	diff_tree_sha1(commit->tree->object.sha1, parent->tree->object.sha1,
+		       "", &diff_opts);
+	diffcore_std(&diff_opts);
+
+	for (i = 0; i < diff_queued_diff.nr; i++) {
+		struct diff_filepair *p = diff_queued_diff.queue[i];
+
+		if (p->status == 'R' && !strcmp(p->one->path, cutil->pathname)) {
+			if (DEBUG)
+				printf("rename %s -> %s\n", p->one->path, p->two->path);
+			return p->two->path;
+		}
+	}
+
+	return 0;
+}
+
+static void simplify_commit(struct rev_info *revs, struct commit *commit)
+{
+	struct commit_list **pp, *parent;
+
+	if (!commit->tree)
+		return;
+
+	if (!commit->parents) {
+		struct util_info* util = commit->object.util;
+		if (!same_tree_as_empty_path(revs, commit->tree,
+					     util->pathname))
+			commit->object.flags |= TREECHANGE;
+		return;
+	}
+
+	pp = &commit->parents;
+	while ((parent = *pp) != NULL) {
+		struct commit *p = parent->item;
+
+		if (p->object.flags & UNINTERESTING) {
+			pp = &parent->next;
+			continue;
+		}
+
+		parse_commit(p);
+		switch (compare_tree_path(revs, p, commit)) {
+		case REV_TREE_SAME:
+			parent->next = NULL;
+			commit->parents = parent;
+			get_util(p)->pathname = get_util(commit)->pathname;
+			return;
+
+		case REV_TREE_NEW:
+		{
+
+			struct util_info* util = commit->object.util;
+			if (revs->remove_empty_trees &&
+			    same_tree_as_empty_path(revs, p->tree,
+						    util->pathname)) {
+				const char* new_name = find_rename(commit, p);
+				if (new_name) {
+					struct util_info* putil = get_util(p);
+					if (!putil->pathname)
+						putil->pathname = strdup(new_name);
+				} else {
+					*pp = parent->next;
+					continue;
+				}
+			}
+		}
+
+		/* fallthrough */
+		case REV_TREE_DIFFERENT:
+			pp = &parent->next;
+			if (!get_util(p)->pathname)
+				get_util(p)->pathname =
+					get_util(commit)->pathname;
+			continue;
+		}
+		die("bad tree compare for commit %s",
+		    sha1_to_hex(commit->object.sha1));
+	}
+	commit->object.flags |= TREECHANGE;
+}
+
+
 struct commit_info
 {
 	char* author;
@@ -569,6 +711,18 @@ static const char* format_time(unsigned long time, const char* tz_str)
 	return time_buf;
 }
 
+static void topo_setter(struct commit* c, void* data)
+{
+	struct util_info* util = c->object.util;
+	util->topo_data = data;
+}
+
+static void* topo_getter(struct commit* c)
+{
+	struct util_info* util = c->object.util;
+	return util->topo_data;
+}
+
 int main(int argc, const char **argv)
 {
 	int i;
@@ -580,8 +734,8 @@ int main(int argc, const char **argv)
 	int sha1_len = 8;
 	int compability = 0;
 	int options = 1;
+	struct commit* start_commit;
 
-	int num_args;
 	const char* args[10];
 	struct rev_info rev;
 
@@ -634,28 +788,29 @@ int main(int argc, const char **argv)
 		strcpy(filename_buf, filename);
 	filename = filename_buf;
 
-	{
-		struct commit* c;
-		if (get_sha1(commit, sha1))
-			die("get_sha1 failed, commit '%s' not found", commit);
-		c = lookup_commit_reference(sha1);
-
-		if (fill_util_info(c, filename)) {
-			printf("%s not found in %s\n", filename, commit);
-			return 1;
-		}
+	if (get_sha1(commit, sha1))
+		die("get_sha1 failed, commit '%s' not found", commit);
+	start_commit = lookup_commit_reference(sha1);
+	get_util(start_commit)->pathname = filename;
+	if (fill_util_info(start_commit)) {
+		printf("%s not found in %s\n", filename, commit);
+		return 1;
 	}
 
-	num_args = 0;
-	args[num_args++] = NULL;
-	args[num_args++] = "--topo-order";
-	args[num_args++] = "--remove-empty";
-	args[num_args++] = commit;
-	args[num_args++] = "--";
-	args[num_args++] = filename;
-	args[num_args] = NULL;
 
-	setup_revisions(num_args, args, &rev, "HEAD");
+	init_revisions(&rev);
+	rev.remove_empty_trees = 1;
+	rev.topo_order = 1;
+	rev.prune_fn = simplify_commit;
+	rev.topo_setter = topo_setter;
+	rev.topo_getter = topo_getter;
+	rev.limited = 1;
+
+	commit_list_insert(start_commit, &rev.commits);
+
+	args[0] = filename;
+	args[1] = NULL;
+	diff_tree_setup_paths(args);
 	prepare_revision_walk(&rev);
 	process_commits(&rev, filename, &initial);
 
@@ -665,17 +820,21 @@ int main(int argc, const char **argv)
 
 	for (i = 0; i < num_blame_lines; i++) {
 		struct commit *c = blame_lines[i];
+		struct util_info* u;
+
 		if (!c)
 			c = initial;
 
+		u = c->object.util;
 		get_commit_info(c, &ci);
 		fwrite(sha1_to_hex(c->object.sha1), sha1_len, 1, stdout);
 		if(compability)
 			printf("\t(%10s\t%10s\t%d)", ci.author,
 			       format_time(ci.author_time, ci.author_tz), i+1);
 		else
-			printf(" (%-15.15s %10s %*d) ", ci.author,
-			       format_time(ci.author_time, ci.author_tz),
+			printf(" %s (%-15.15s %10s %*d) ", u->pathname,
+			       ci.author, format_time(ci.author_time,
+						      ci.author_tz),
 			       max_digits, i+1);
 
 		if(i == num_blame_lines - 1) {
diff --git a/commit.c b/commit.c
index 06d5439152..eb42d517a4 100644
--- a/commit.c
+++ b/commit.c
@@ -569,10 +569,28 @@ int count_parents(struct commit * commit)
         return count;
 }
 
+void topo_sort_default_setter(struct commit *c, void *data)
+{
+	c->object.util = data;
+}
+
+void *topo_sort_default_getter(struct commit *c)
+{
+	return c->object.util;
+}
+
 /*
  * Performs an in-place topological sort on the list supplied.
  */
 void sort_in_topological_order(struct commit_list ** list, int lifo)
+{
+	sort_in_topological_order_fn(list, lifo, topo_sort_default_setter,
+				     topo_sort_default_getter);
+}
+
+void sort_in_topological_order_fn(struct commit_list ** list, int lifo,
+				  topo_sort_set_fn_t setter,
+				  topo_sort_get_fn_t getter)
 {
 	struct commit_list * next = *list;
 	struct commit_list * work = NULL, **insert;
@@ -596,7 +614,7 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
 	next=*list;
 	while (next) {
 		next_nodes->list_item = next;
-		next->item->object.util = next_nodes;
+		setter(next->item, next_nodes);
 		next_nodes++;
 		next = next->next;
 	}
@@ -606,8 +624,8 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
 		struct commit_list * parents = next->item->parents;
 		while (parents) {
 			struct commit * parent=parents->item;
-			struct sort_node * pn = (struct sort_node *)parent->object.util;
-			
+			struct sort_node * pn = (struct sort_node *) getter(parent);
+
 			if (pn)
 				pn->indegree++;
 			parents=parents->next;
@@ -624,7 +642,7 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
 	next=*list;
 	insert = &work;
 	while (next) {
-		struct sort_node * node = (struct sort_node *)next->item->object.util;
+		struct sort_node * node = (struct sort_node *) getter(next->item);
 
 		if (node->indegree == 0) {
 			insert = &commit_list_insert(next->item, insert)->next;
@@ -637,15 +655,15 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
 		sort_by_date(&work);
 	while (work) {
 		struct commit * work_item = pop_commit(&work);
-		struct sort_node * work_node = (struct sort_node *)work_item->object.util;
+		struct sort_node * work_node = (struct sort_node *) getter(work_item);
 		struct commit_list * parents = work_item->parents;
 
 		while (parents) {
 			struct commit * parent=parents->item;
-			struct sort_node * pn = (struct sort_node *)parent->object.util;
-			
+			struct sort_node * pn = (struct sort_node *) getter(parent);
+
 			if (pn) {
-				/* 
+				/*
 				 * parents are only enqueued for emission 
                                  * when all their children have been emitted thereby
                                  * guaranteeing topological order.
@@ -667,7 +685,7 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
 		*pptr = work_node->list_item;
 		pptr = &(*pptr)->next;
 		*pptr = NULL;
-		work_item->object.util = NULL;
+		setter(work_item, NULL);
 	}
 	free(nodes);
 }
diff --git a/commit.h b/commit.h
index 70a7c75e65..98682b232a 100644
--- a/commit.h
+++ b/commit.h
@@ -65,15 +65,29 @@ int count_parents(struct commit * commit);
 /*
  * Performs an in-place topological sort of list supplied.
  *
- * Pre-conditions:
+ * Pre-conditions for sort_in_topological_order:
  *   all commits in input list and all parents of those
  *   commits must have object.util == NULL
- *        
- * Post-conditions: 
+ *
+ * Pre-conditions for sort_in_topological_order_fn:
+ *   all commits in input list and all parents of those
+ *   commits must have getter(commit) == NULL
+ *
+ * Post-conditions:
  *   invariant of resulting list is:
  *      a reachable from b => ord(b) < ord(a)
  *   in addition, when lifo == 0, commits on parallel tracks are
  *   sorted in the dates order.
  */
+
+typedef void (*topo_sort_set_fn_t)(struct commit*, void *data);
+typedef void* (*topo_sort_get_fn_t)(struct commit*);
+
+void topo_sort_default_setter(struct commit *c, void *data);
+void *topo_sort_default_getter(struct commit *c);
+
 void sort_in_topological_order(struct commit_list ** list, int lifo);
+void sort_in_topological_order_fn(struct commit_list ** list, int lifo,
+				  topo_sort_set_fn_t setter,
+				  topo_sort_get_fn_t getter);
 #endif /* COMMIT_H */
diff --git a/count-delta.c b/count-delta.c
deleted file mode 100644
index 058a2aadb1..0000000000
--- a/count-delta.c
+++ /dev/null
@@ -1,72 +0,0 @@
-/*
- * Copyright (C) 2005 Junio C Hamano
- * The delta-parsing part is almost straight copy of patch-delta.c
- * which is (C) 2005 Nicolas Pitre <nico@cam.org>.
- */
-#include <stdlib.h>
-#include <string.h>
-#include <limits.h>
-#include "delta.h"
-#include "count-delta.h"
-
-/*
- * NOTE.  We do not _interpret_ delta fully.  As an approximation, we
- * just count the number of bytes that are copied from the source, and
- * the number of literal data bytes that are inserted.
- *
- * Number of bytes that are _not_ copied from the source is deletion,
- * and number of inserted literal bytes are addition, so sum of them
- * is the extent of damage.
- */
-int count_delta(void *delta_buf, unsigned long delta_size,
-		unsigned long *src_copied, unsigned long *literal_added)
-{
-	unsigned long copied_from_source, added_literal;
-	const unsigned char *data, *top;
-	unsigned char cmd;
-	unsigned long src_size, dst_size, out;
-
-	if (delta_size < DELTA_SIZE_MIN)
-		return -1;
-
-	data = delta_buf;
-	top = delta_buf + delta_size;
-
-	src_size = get_delta_hdr_size(&data);
-	dst_size = get_delta_hdr_size(&data);
-
-	added_literal = copied_from_source = out = 0;
-	while (data < top) {
-		cmd = *data++;
-		if (cmd & 0x80) {
-			unsigned long cp_off = 0, cp_size = 0;
-			if (cmd & 0x01) cp_off = *data++;
-			if (cmd & 0x02) cp_off |= (*data++ << 8);
-			if (cmd & 0x04) cp_off |= (*data++ << 16);
-			if (cmd & 0x08) cp_off |= (*data++ << 24);
-			if (cmd & 0x10) cp_size = *data++;
-			if (cmd & 0x20) cp_size |= (*data++ << 8);
-			if (cmd & 0x40) cp_size |= (*data++ << 16);
-			if (cp_size == 0) cp_size = 0x10000;
-
-			copied_from_source += cp_size;
-			out += cp_size;
-		} else {
-			/* write literal into dst */
-			added_literal += cmd;
-			out += cmd;
-			data += cmd;
-		}
-	}
-
-	/* sanity check */
-	if (data != top || out != dst_size)
-		return -1;
-
-	/* delete size is what was _not_ copied from source.
-	 * edit size is that and literal additions.
-	 */
-	*src_copied = copied_from_source;
-	*literal_added = added_literal;
-	return 0;
-}
diff --git a/count-delta.h b/count-delta.h
deleted file mode 100644
index 7359629827..0000000000
--- a/count-delta.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/*
- * Copyright (C) 2005 Junio C Hamano
- */
-#ifndef COUNT_DELTA_H
-#define COUNT_DELTA_H
-
-int count_delta(void *, unsigned long,
-		unsigned long *src_copied, unsigned long *literal_added);
-
-#endif
diff --git a/diffcore-break.c b/diffcore-break.c
index 0fc2b860be..71ad58a25a 100644
--- a/diffcore-break.c
+++ b/diffcore-break.c
@@ -45,8 +45,8 @@ static int should_break(struct diff_filespec *src,
 	 * The value we return is 1 if we want the pair to be broken,
 	 * or 0 if we do not.
 	 */
-	unsigned long delta_size, base_size, src_copied, literal_added;
-	int to_break = 0;
+	unsigned long delta_size, base_size, src_copied, literal_added,
+		src_removed;
 
 	*merge_score_p = 0; /* assume no deletion --- "do not break"
 			     * is the default.
@@ -72,33 +72,40 @@ static int should_break(struct diff_filespec *src,
 				   &src_copied, &literal_added))
 		return 0;
 
+	/* sanity */
+	if (src->size < src_copied)
+		src_copied = src->size;
+	if (dst->size < literal_added + src_copied) {
+		if (src_copied < dst->size)
+			literal_added = dst->size - src_copied;
+		else
+			literal_added = 0;
+	}
+	src_removed = src->size - src_copied;
+
 	/* Compute merge-score, which is "how much is removed
 	 * from the source material".  The clean-up stage will
 	 * merge the surviving pair together if the score is
 	 * less than the minimum, after rename/copy runs.
 	 */
-	if (src->size <= src_copied)
-		; /* all copied, nothing removed */
-	else {
-		delta_size = src->size - src_copied;
-		*merge_score_p = delta_size * MAX_SCORE / src->size;
-	}
-	
+	*merge_score_p = src_removed * MAX_SCORE / src->size;
+
 	/* Extent of damage, which counts both inserts and
 	 * deletes.
 	 */
-	if (src->size + literal_added <= src_copied)
-		delta_size = 0; /* avoid wrapping around */
-	else
-		delta_size = (src->size - src_copied) + literal_added;
-	
-	/* We break if the edit exceeds the minimum.
-	 * i.e. (break_score / MAX_SCORE < delta_size / base_size)
+	delta_size = src_removed + literal_added;
+	if (delta_size * MAX_SCORE / base_size < break_score)
+		return 0;
+
+	/* If you removed a lot without adding new material, that is
+	 * not really a rewrite.
 	 */
-	if (break_score * base_size < delta_size * MAX_SCORE)
-		to_break = 1;
+	if ((src->size * break_score < src_removed * MAX_SCORE) &&
+	    (literal_added * 20 < src_removed) &&
+	    (literal_added * 20 < src_copied))
+		return 0;
 
-	return to_break;
+	return 1;
 }
 
 void diffcore_break(int break_score)
diff --git a/diffcore-delta.c b/diffcore-delta.c
index 1e6a6911ec..70bacff837 100644
--- a/diffcore-delta.c
+++ b/diffcore-delta.c
@@ -1,32 +1,53 @@
 #include "cache.h"
 #include "diff.h"
 #include "diffcore.h"
-#include "delta.h"
-#include "count-delta.h"
-
-static int diffcore_count_changes_1(void *src, unsigned long src_size,
-				    void *dst, unsigned long dst_size,
-				    unsigned long delta_limit,
-				    unsigned long *src_copied,
-				    unsigned long *literal_added)
+
+/*
+ * Idea here is very simple.
+ *
+ * We have total of (sz-N+1) N-byte overlapping sequences in buf whose
+ * size is sz.  If the same N-byte sequence appears in both source and
+ * destination, we say the byte that starts that sequence is shared
+ * between them (i.e. copied from source to destination).
+ *
+ * For each possible N-byte sequence, if the source buffer has more
+ * instances of it than the destination buffer, that means the
+ * difference are the number of bytes not copied from source to
+ * destination.  If the counts are the same, everything was copied
+ * from source to destination.  If the destination has more,
+ * everything was copied, and destination added more.
+ *
+ * We are doing an approximation so we do not really have to waste
+ * memory by actually storing the sequence.  We just hash them into
+ * somewhere around 2^16 hashbuckets and count the occurrences.
+ *
+ * The length of the sequence is arbitrarily set to 8 for now.
+ */
+
+#define HASHBASE 65537 /* next_prime(2^16) */
+
+static void hash_chars(unsigned char *buf, unsigned long sz, int *count)
 {
-	void *delta;
-	unsigned long delta_size;
-
-	delta = diff_delta(src, src_size,
-			   dst, dst_size,
-			   &delta_size, delta_limit);
-	if (!delta)
-		/* If delta_limit is exceeded, we have too much differences */
-		return -1;
+	unsigned int accum1, accum2, i;
 
-	/* Estimate the edit size by interpreting delta. */
-	if (count_delta(delta, delta_size, src_copied, literal_added)) {
-		free(delta);
-		return -1;
+	/* an 8-byte shift register made of accum1 and accum2.  New
+	 * bytes come at LSB of accum2, and shifted up to accum1
+	 */
+	for (i = accum1 = accum2 = 0; i < 7; i++, sz--) {
+		accum1 = (accum1 << 8) | (accum2 >> 24);
+		accum2 = (accum2 << 8) | *buf++;
+	}
+	while (sz) {
+		accum1 = (accum1 << 8) | (accum2 >> 24);
+		accum2 = (accum2 << 8) | *buf++;
+		/* We want something that hashes permuted byte
+		 * sequences nicely; simpler hash like (accum1 ^
+		 * accum2) does not perform as well.
+		 */
+		i = (accum1 + accum2 * 0x61) % HASHBASE;
+		count[i]++;
+		sz--;
 	}
-	free(delta);
-	return 0;
 }
 
 int diffcore_count_changes(void *src, unsigned long src_size,
@@ -35,9 +56,28 @@ int diffcore_count_changes(void *src, unsigned long src_size,
 			   unsigned long *src_copied,
 			   unsigned long *literal_added)
 {
-	return diffcore_count_changes_1(src, src_size,
-					dst, dst_size,
-					delta_limit,
-					src_copied,
-					literal_added);
+	int *src_count, *dst_count, i;
+	unsigned long sc, la;
+
+	if (src_size < 8 || dst_size < 8)
+		return -1;
+
+	src_count = xcalloc(HASHBASE * 2, sizeof(int));
+	dst_count = src_count + HASHBASE;
+	hash_chars(src, src_size, src_count);
+	hash_chars(dst, dst_size, dst_count);
+
+	sc = la = 0;
+	for (i = 0; i < HASHBASE; i++) {
+		if (src_count[i] < dst_count[i]) {
+			la += dst_count[i] - src_count[i];
+			sc += src_count[i];
+		}
+		else /* i.e. if (dst_count[i] <= src_count[i]) */
+			sc += dst_count[i];
+	}
+	*src_copied = sc;
+	*literal_added = la;
+	free(src_count);
+	return 0;
 }
diff --git a/diffcore-rename.c b/diffcore-rename.c
index 55cf1c37f3..625b589fb7 100644
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -170,19 +170,15 @@ static int estimate_similarity(struct diff_filespec *src,
 				   &src_copied, &literal_added))
 		return 0;
 
-	/* Extent of damage */
-	if (src->size + literal_added < src_copied)
-		delta_size = 0;
-	else
-		delta_size = (src->size - src_copied) + literal_added;
-
-	/*
-	 * Now we will give some score to it.  100% edit gets 0 points
-	 * and 0% edit gets MAX_SCORE points.
+	/* How similar are they?
+	 * what percentage of material in dst are from source?
 	 */
-	score = MAX_SCORE - (MAX_SCORE * delta_size / base_size); 
-	if (score < 0) return 0;
-	if (MAX_SCORE < score) return MAX_SCORE;
+	if (dst->size < src_copied)
+		score = MAX_SCORE;
+	else if (!dst->size)
+		score = 0; /* should not happen */
+	else
+		score = src_copied * MAX_SCORE / dst->size;
 	return score;
 }
 
diff --git a/diffcore.h b/diffcore.h
index dba4f17658..d31b3b476c 100644
--- a/diffcore.h
+++ b/diffcore.h
@@ -17,8 +17,8 @@
  */
 #define MAX_SCORE 60000.0
 #define DEFAULT_RENAME_SCORE 30000 /* rename/copy similarity minimum (50%) */
-#define DEFAULT_BREAK_SCORE  30000 /* minimum for break to happen (50%)*/
-#define DEFAULT_MERGE_SCORE  48000 /* maximum for break-merge to happen (80%)*/
+#define DEFAULT_BREAK_SCORE  30000 /* minimum for break to happen (50%) */
+#define DEFAULT_MERGE_SCORE  36000 /* maximum for break-merge to happen 60%) */
 
 #define MINIMUM_BREAK_SIZE     400 /* do not break a file smaller than this */
 
diff --git a/fsck-objects.c b/fsck-objects.c
index 4ddd67699c..59b25904cb 100644
--- a/fsck-objects.c
+++ b/fsck-objects.c
@@ -14,10 +14,9 @@
 static int show_root = 0;
 static int show_tags = 0;
 static int show_unreachable = 0;
-static int standalone = 0;
 static int check_full = 0;
 static int check_strict = 0;
-static int keep_cache_objects = 0; 
+static int keep_cache_objects = 0;
 static unsigned char head_sha1[20];
 
 #ifdef NO_D_INO_IN_DIRENT
@@ -68,7 +67,7 @@ static void check_connectivity(void)
 			continue;
 
 		if (!obj->parsed) {
-			if (!standalone && has_sha1_file(obj->sha1))
+			if (has_sha1_file(obj->sha1))
 				; /* it is in pack */
 			else
 				printf("missing %s %s\n",
@@ -82,7 +81,7 @@ static void check_connectivity(void)
 			for (j = 0; j < refs->count; j++) {
 				struct object *ref = refs->ref[j];
 				if (ref->parsed ||
-				    (!standalone && has_sha1_file(ref->sha1)))
+				    (has_sha1_file(ref->sha1)))
 					continue;
 				printf("broken link from %7s %s\n",
 				       obj->type, sha1_to_hex(obj->sha1));
@@ -390,7 +389,7 @@ static int fsck_handle_ref(const char *refname, const unsigned char *sha1)
 
 	obj = lookup_object(sha1);
 	if (!obj) {
-		if (!standalone && has_sha1_file(sha1)) {
+		if (has_sha1_file(sha1)) {
 			default_refs++;
 			return 0; /* it is in a pack */
 		}
@@ -464,10 +463,6 @@ int main(int argc, char **argv)
 			keep_cache_objects = 1;
 			continue;
 		}
-		if (!strcmp(arg, "--standalone")) {
-			standalone = 1;
-			continue;
-		}
 		if (!strcmp(arg, "--full")) {
 			check_full = 1;
 			continue;
@@ -477,14 +472,9 @@ int main(int argc, char **argv)
 			continue;
 		}
 		if (*arg == '-')
-			usage("git-fsck-objects [--tags] [--root] [[--unreachable] [--cache] [--standalone | --full] [--strict] <head-sha1>*]");
+			usage("git-fsck-objects [--tags] [--root] [[--unreachable] [--cache] [--full] [--strict] <head-sha1>*]");
 	}
 
-	if (standalone && check_full)
-		die("Only one of --standalone or --full can be used.");
-	if (standalone)
-		putenv("GIT_ALTERNATE_OBJECT_DIRECTORIES=");
-
 	fsck_head_link();
 	fsck_object_dir(get_object_directory());
 	if (check_full) {
diff --git a/git-fetch.sh b/git-fetch.sh
index 0346d4a45c..c0eb96752e 100755
--- a/git-fetch.sh
+++ b/git-fetch.sh
@@ -94,6 +94,9 @@ append_fetch_head () {
     # remote-nick is the URL given on the command line (or a shorthand)
     # remote-name is the $GIT_DIR relative refs/ path we computed
     # for this refspec.
+
+    # the $note_ variable will be fed to git-fmt-merge-msg for further
+    # processing.
     case "$remote_name_" in
     HEAD)
 	note_= ;;
@@ -103,6 +106,9 @@ append_fetch_head () {
     refs/tags/*)
 	note_="$(expr "$remote_name_" : 'refs/tags/\(.*\)')"
 	note_="tag '$note_' of " ;;
+    refs/remotes/*)
+	note_="$(expr "$remote_name_" : 'refs/remotes/\(.*\)')"
+	note_="remote branch '$note_' of " ;;
     *)
 	note_="$remote_name of " ;;
     esac
@@ -147,10 +153,10 @@ fast_forward_local () {
 	else
 		echo >&2 "* $1: storing $3"
 	fi
-	git-update-ref "$1" "$2" 
+	git-update-ref "$1" "$2"
 	;;
 
-    refs/heads/*)
+    refs/heads/* | refs/remotes/*)
 	# $1 is the ref being updated.
 	# $2 is the new value for the ref.
 	local=$(git-rev-parse --verify "$1^0" 2>/dev/null)
diff --git a/git-fmt-merge-msg.perl b/git-fmt-merge-msg.perl
index afe80e6321..5986e5414a 100755
--- a/git-fmt-merge-msg.perl
+++ b/git-fmt-merge-msg.perl
@@ -75,6 +75,7 @@ sub shortlog {
 		$src{$src} = {
 			BRANCH => [],
 			TAG => [],
+			R_BRANCH => [],
 			GENERIC => [],
 			# &1 == has HEAD.
 			# &2 == has others.
@@ -91,6 +92,11 @@ sub shortlog {
 		push @{$src{$src}{TAG}}, $1;
 		$src{$src}{HEAD_STATUS} |= 2;
 	}
+	elsif (/^remote branch (.*)$/) {
+		$origin = $1;
+		push @{$src{$src}{R_BRANCH}}, $1;
+		$src{$src}{HEAD_STATUS} |= 2;
+	}
 	elsif (/^HEAD$/) {
 		$origin = $src;
 		$src{$src}{HEAD_STATUS} |= 1;
@@ -123,6 +129,8 @@ sub shortlog {
 	}
 	push @this, andjoin("branch ", "branches ",
 			   $src{$src}{BRANCH});
+	push @this, andjoin("remote branch ", "remote branches ",
+			   $src{$src}{R_BRANCH});
 	push @this, andjoin("tag ", "tags ",
 			   $src{$src}{TAG});
 	push @this, andjoin("commit ", "commits ",
diff --git a/git-parse-remote.sh b/git-parse-remote.sh
index 5f158c613f..63f22818e6 100755
--- a/git-parse-remote.sh
+++ b/git-parse-remote.sh
@@ -86,14 +86,14 @@ canon_refs_list_for_fetch () {
 		local=$(expr "$ref" : '[^:]*:\(.*\)')
 		case "$remote" in
 		'') remote=HEAD ;;
-		refs/heads/* | refs/tags/*) ;;
-		heads/* | tags/* ) remote="refs/$remote" ;;
+		refs/heads/* | refs/tags/* | refs/remotes/*) ;;
+		heads/* | tags/* | remotes/* ) remote="refs/$remote" ;;
 		*) remote="refs/heads/$remote" ;;
 		esac
 		case "$local" in
 		'') local= ;;
-		refs/heads/* | refs/tags/*) ;;
-		heads/* | tags/* ) local="refs/$local" ;;
+		refs/heads/* | refs/tags/* | refs/remotes/*) ;;
+		heads/* | tags/* | remotes/* ) local="refs/$local" ;;
 		*) local="refs/heads/$local" ;;
 		esac
 
diff --git a/pack-check.c b/pack-check.c
index eca32b6cab..84ed90d369 100644
--- a/pack-check.c
+++ b/pack-check.c
@@ -70,13 +70,17 @@ static int verify_packfile(struct packed_git *p)
 }
 
 
+#define MAX_CHAIN 40
+
 static void show_pack_info(struct packed_git *p)
 {
 	struct pack_header *hdr;
 	int nr_objects, i;
+	unsigned int chain_histogram[MAX_CHAIN];
 
 	hdr = p->pack_base;
 	nr_objects = ntohl(hdr->hdr_entries);
+	memset(chain_histogram, 0, sizeof(chain_histogram));
 
 	for (i = 0; i < nr_objects; i++) {
 		unsigned char sha1[20], base_sha1[20];
@@ -97,11 +101,25 @@ static void show_pack_info(struct packed_git *p)
 		printf("%s ", sha1_to_hex(sha1));
 		if (!delta_chain_length)
 			printf("%-6s %lu %u\n", type, size, e.offset);
-		else
+		else {
 			printf("%-6s %lu %u %u %s\n", type, size, e.offset,
 			       delta_chain_length, sha1_to_hex(base_sha1));
+			if (delta_chain_length < MAX_CHAIN)
+				chain_histogram[delta_chain_length]++;
+			else
+				chain_histogram[0]++;
+		}
 	}
 
+	for (i = 0; i < MAX_CHAIN; i++) {
+		if (!chain_histogram[i])
+			continue;
+		printf("chain length %s %d: %d object%s\n",
+		       i ? "=" : ">=",
+		       i ? i : MAX_CHAIN,
+		       chain_histogram[i],
+		       1 < chain_histogram[i] ? "s" : "");
+	}
 }
 
 int verify_pack(struct packed_git *p, int verbose)
diff --git a/pack-objects.c b/pack-objects.c
index 136a7f5aad..49357c6735 100644
--- a/pack-objects.c
+++ b/pack-objects.c
@@ -32,9 +32,6 @@ struct object_entry {
 				 * be used as the base objectto delta huge
 				 * objects against.
 				 */
-	int based_on_preferred;	/* current delta candidate is a preferred
-				 * one, or delta against a preferred one.
-				 */
 };
 
 /*
@@ -824,8 +821,6 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de
 {
 	struct object_entry *cur_entry = cur->entry;
 	struct object_entry *old_entry = old->entry;
-	int old_preferred = (old_entry->preferred_base ||
-			     old_entry->based_on_preferred);
 	unsigned long size, oldsize, delta_size, sizediff;
 	long max_size;
 	void *delta_buf;
@@ -867,27 +862,8 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de
 	 * delete).
 	 */
 	max_size = size / 2 - 20;
-	if (cur_entry->delta) {
-		if (cur_entry->based_on_preferred) {
-			if (old_preferred)
-				max_size = cur_entry->delta_size-1;
-			else
-				/* trying with non-preferred one when we
-				 * already have a delta based on preferred
-				 * one is pointless.
-				 */
-				return -1;
-		}
-		else if (!old_preferred)
-			max_size = cur_entry->delta_size-1;
-		else
-			/* otherwise...  even if delta with a
-			 * preferred one produces a bigger result than
-			 * what we currently have, which is based on a
-			 * non-preferred one, it is OK.
-			 */
-			;
-	}
+	if (cur_entry->delta)
+		max_size = cur_entry->delta_size-1;
 	if (sizediff >= max_size)
 		return -1;
 	delta_buf = diff_delta(old->data, oldsize,
@@ -897,7 +873,6 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de
 	cur_entry->delta = old_entry;
 	cur_entry->delta_size = delta_size;
 	cur_entry->depth = old_entry->depth + 1;
-	cur_entry->based_on_preferred = old_preferred;
 	free(delta_buf);
 	return 0;
 }
@@ -966,6 +941,15 @@ static void find_deltas(struct object_entry **list, int window, int depth)
 			if (try_delta(n, m, depth) < 0)
 				break;
 		}
+#if 0
+		/* if we made n a delta, and if n is already at max
+		 * depth, leaving it in the window is pointless.  we
+		 * should evict it first.
+		 * ... in theory only; somehow this makes things worse.
+		 */
+		if (entry->delta && depth <= entry->depth)
+			continue;
+#endif
 		idx++;
 		if (idx >= window)
 			idx = 0;
diff --git a/rev-list.c b/rev-list.c
index 8e4d83efba..812d237f47 100644
--- a/rev-list.c
+++ b/rev-list.c
@@ -190,7 +190,7 @@ static int count_distance(struct commit_list *entry)
 
 		if (commit->object.flags & (UNINTERESTING | COUNTED))
 			break;
-		if (!revs.paths || (commit->object.flags & TREECHANGE))
+		if (!revs.prune_fn || (commit->object.flags & TREECHANGE))
 			nr++;
 		commit->object.flags |= COUNTED;
 		p = commit->parents;
@@ -224,7 +224,7 @@ static struct commit_list *find_bisection(struct commit_list *list)
 	nr = 0;
 	p = list;
 	while (p) {
-		if (!revs.paths || (p->item->object.flags & TREECHANGE))
+		if (!revs.prune_fn || (p->item->object.flags & TREECHANGE))
 			nr++;
 		p = p->next;
 	}
@@ -234,7 +234,7 @@ static struct commit_list *find_bisection(struct commit_list *list)
 	for (p = list; p; p = p->next) {
 		int distance;
 
-		if (revs.paths && !(p->item->object.flags & TREECHANGE))
+		if (revs.prune_fn && !(p->item->object.flags & TREECHANGE))
 			continue;
 
 		distance = count_distance(p);
diff --git a/revision.c b/revision.c
index c8d93ff106..01386ed6d4 100644
--- a/revision.c
+++ b/revision.c
@@ -199,31 +199,27 @@ static int everybody_uninteresting(struct commit_list *orig)
 	return 1;
 }
 
-#define TREE_SAME	0
-#define TREE_NEW	1
-#define TREE_DIFFERENT	2
-static int tree_difference = TREE_SAME;
+static int tree_difference = REV_TREE_SAME;
 
 static void file_add_remove(struct diff_options *options,
 		    int addremove, unsigned mode,
 		    const unsigned char *sha1,
 		    const char *base, const char *path)
 {
-	int diff = TREE_DIFFERENT;
+	int diff = REV_TREE_DIFFERENT;
 
 	/*
-	 * Is it an add of a new file? It means that
-	 * the old tree didn't have it at all, so we
-	 * will turn "TREE_SAME" -> "TREE_NEW", but
-	 * leave any "TREE_DIFFERENT" alone (and if
-	 * it already was "TREE_NEW", we'll keep it
-	 * "TREE_NEW" of course).
+	 * Is it an add of a new file? It means that the old tree
+	 * didn't have it at all, so we will turn "REV_TREE_SAME" ->
+	 * "REV_TREE_NEW", but leave any "REV_TREE_DIFFERENT" alone
+	 * (and if it already was "REV_TREE_NEW", we'll keep it
+	 * "REV_TREE_NEW" of course).
 	 */
 	if (addremove == '+') {
 		diff = tree_difference;
-		if (diff != TREE_SAME)
+		if (diff != REV_TREE_SAME)
 			return;
-		diff = TREE_NEW;
+		diff = REV_TREE_NEW;
 	}
 	tree_difference = diff;
 }
@@ -234,7 +230,7 @@ static void file_change(struct diff_options *options,
 		 const unsigned char *new_sha1,
 		 const char *base, const char *path)
 {
-	tree_difference = TREE_DIFFERENT;
+	tree_difference = REV_TREE_DIFFERENT;
 }
 
 static struct diff_options diff_opt = {
@@ -243,19 +239,19 @@ static struct diff_options diff_opt = {
 	.change = file_change,
 };
 
-static int compare_tree(struct tree *t1, struct tree *t2)
+int rev_compare_tree(struct tree *t1, struct tree *t2)
 {
 	if (!t1)
-		return TREE_NEW;
+		return REV_TREE_NEW;
 	if (!t2)
-		return TREE_DIFFERENT;
-	tree_difference = TREE_SAME;
+		return REV_TREE_DIFFERENT;
+	tree_difference = REV_TREE_SAME;
 	if (diff_tree_sha1(t1->object.sha1, t2->object.sha1, "", &diff_opt) < 0)
-		return TREE_DIFFERENT;
+		return REV_TREE_DIFFERENT;
 	return tree_difference;
 }
 
-static int same_tree_as_empty(struct tree *t1)
+int rev_same_tree_as_empty(struct tree *t1)
 {
 	int retval;
 	void *tree;
@@ -288,7 +284,7 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit)
 		return;
 
 	if (!commit->parents) {
-		if (!same_tree_as_empty(commit->tree))
+		if (!rev_same_tree_as_empty(commit->tree))
 			commit->object.flags |= TREECHANGE;
 		return;
 	}
@@ -298,8 +294,8 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit)
 		struct commit *p = parent->item;
 
 		parse_commit(p);
-		switch (compare_tree(p->tree, commit->tree)) {
-		case TREE_SAME:
+		switch (rev_compare_tree(p->tree, commit->tree)) {
+		case REV_TREE_SAME:
 			if (p->object.flags & UNINTERESTING) {
 				/* Even if a merge with an uninteresting
 				 * side branch brought the entire change
@@ -314,13 +310,14 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit)
 			commit->parents = parent;
 			return;
 
-		case TREE_NEW:
-			if (revs->remove_empty_trees && same_tree_as_empty(p->tree)) {
+		case REV_TREE_NEW:
+			if (revs->remove_empty_trees &&
+			    rev_same_tree_as_empty(p->tree)) {
 				*pp = parent->next;
 				continue;
 			}
 		/* fallthrough */
-		case TREE_DIFFERENT:
+		case REV_TREE_DIFFERENT:
 			tree_changed = 1;
 			pp = &parent->next;
 			continue;
@@ -368,8 +365,8 @@ static void add_parents_to_list(struct rev_info *revs, struct commit *commit, st
 	 * simplify the commit history and find the parent
 	 * that has no differences in the path set if one exists.
 	 */
-	if (revs->paths)
-		try_to_simplify_commit(revs, commit);
+	if (revs->prune_fn)
+		revs->prune_fn(revs, commit);
 
 	parent = commit->parents;
 	while (parent) {
@@ -391,9 +388,6 @@ static void limit_list(struct rev_info *revs)
 	struct commit_list *newlist = NULL;
 	struct commit_list **p = &newlist;
 
-	if (revs->paths)
-		diff_tree_setup_paths(revs->paths);
-
 	while (list) {
 		struct commit_list *entry = list;
 		struct commit *commit = list->item;
@@ -445,6 +439,23 @@ static void handle_all(struct rev_info *revs, unsigned flags)
 	for_each_ref(handle_one_ref);
 }
 
+void init_revisions(struct rev_info *revs)
+{
+	memset(revs, 0, sizeof(*revs));
+	revs->lifo = 1;
+	revs->dense = 1;
+	revs->prefix = setup_git_directory();
+	revs->max_age = -1;
+	revs->min_age = -1;
+	revs->max_count = -1;
+
+	revs->prune_fn = NULL;
+	revs->prune_data = NULL;
+
+	revs->topo_setter = topo_sort_default_setter;
+	revs->topo_getter = topo_sort_default_getter;
+}
+
 /*
  * Parse revision information, filling in the "rev_info" structure,
  * and removing the used arguments from the argument list.
@@ -458,13 +469,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
 	const char **unrecognized = argv + 1;
 	int left = 1;
 
-	memset(revs, 0, sizeof(*revs));
-	revs->lifo = 1;
-	revs->dense = 1;
-	revs->prefix = setup_git_directory();
-	revs->max_age = -1;
-	revs->min_age = -1;
-	revs->max_count = -1;
+	init_revisions(revs);
 
 	/* First, search for "--" */
 	seen_dashdash = 0;
@@ -474,7 +479,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
 			continue;
 		argv[i] = NULL;
 		argc = i;
-		revs->paths = get_pathspec(revs->prefix, argv + i + 1);
+		revs->prune_data = get_pathspec(revs->prefix, argv + i + 1);
 		seen_dashdash = 1;
 		break;
 	}
@@ -638,7 +643,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
 				if (lstat(argv[j], &st) < 0)
 					die("'%s': %s", arg, strerror(errno));
 			}
-			revs->paths = get_pathspec(revs->prefix, argv + i);
+			revs->prune_data = get_pathspec(revs->prefix, argv + i);
 			break;
 		}
 		commit = get_commit_reference(revs, arg, sha1, flags ^ local_flags);
@@ -652,8 +657,13 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
 		commit = get_commit_reference(revs, def, sha1, 0);
 		add_one_commit(commit, revs);
 	}
-	if (revs->paths)
+
+	if (revs->prune_data) {
+		diff_tree_setup_paths(revs->prune_data);
+		revs->prune_fn = try_to_simplify_commit;
 		revs->limited = 1;
+	}
+
 	return left;
 }
 
@@ -663,7 +673,9 @@ void prepare_revision_walk(struct rev_info *revs)
 	if (revs->limited)
 		limit_list(revs);
 	if (revs->topo_order)
-		sort_in_topological_order(&revs->commits, revs->lifo);
+		sort_in_topological_order_fn(&revs->commits, revs->lifo,
+					     revs->topo_setter,
+					     revs->topo_getter);
 }
 
 static int rewrite_one(struct commit **pp)
@@ -719,7 +731,7 @@ struct commit *get_revision(struct rev_info *revs)
 			return NULL;
 		if (revs->no_merges && commit->parents && commit->parents->next)
 			goto next;
-		if (revs->paths && revs->dense) {
+		if (revs->prune_fn && revs->dense) {
 			if (!(commit->object.flags & TREECHANGE))
 				goto next;
 			rewrite_parents(commit);
diff --git a/revision.h b/revision.h
index 31e8f61567..6c2becad13 100644
--- a/revision.h
+++ b/revision.h
@@ -7,6 +7,10 @@
 #define SHOWN		(1u<<3)
 #define TMP_MARK	(1u<<4) /* for isolated cases; clean after use */
 
+struct rev_info;
+
+typedef void (prune_fn_t)(struct rev_info *revs, struct commit *commit);
+
 struct rev_info {
 	/* Starting list */
 	struct commit_list *commits;
@@ -14,7 +18,8 @@ struct rev_info {
 
 	/* Basic information */
 	const char *prefix;
-	const char **paths;
+	void *prune_data;
+	prune_fn_t *prune_fn;
 
 	/* Traversal flags */
 	unsigned int	dense:1,
@@ -33,9 +38,20 @@ struct rev_info {
 	int max_count;
 	unsigned long max_age;
 	unsigned long min_age;
+
+	topo_sort_set_fn_t topo_setter;
+	topo_sort_get_fn_t topo_getter;
 };
 
+#define REV_TREE_SAME		0
+#define REV_TREE_NEW		1
+#define REV_TREE_DIFFERENT	2
+
 /* revision.c */
+extern int rev_same_tree_as_empty(struct tree *t1);
+extern int rev_compare_tree(struct tree *t1, struct tree *t2);
+
+extern void init_revisions(struct rev_info *revs);
 extern int setup_revisions(int argc, const char **argv, struct rev_info *revs, const char *def);
 extern void prepare_revision_walk(struct rev_info *revs);
 extern struct commit *get_revision(struct rev_info *revs);