From 90b4a71c493bf24f11b5edee8a519110624a6bea Mon Sep 17 00:00:00 2001
From: Junio C Hamano <gitster@pobox.com>
Date: Tue, 9 Sep 2008 01:27:07 -0700
Subject: [PATCH 1/4] is_directory(): a generic helper function

A simple "grep -e stat --and -e S_ISDIR" revealed there are many
open-coded implementations of this function.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 abspath.c       | 13 ++++++++++++-
 builtin-clone.c |  9 +--------
 cache.h         |  1 +
 daemon.c        | 10 +++-------
 rerere.c        |  3 +--
 sha1_file.c     |  3 +--
 6 files changed, 19 insertions(+), 20 deletions(-)

diff --git a/abspath.c b/abspath.c
index 0d561246e0..8194ce1256 100644
--- a/abspath.c
+++ b/abspath.c
@@ -1,5 +1,16 @@
 #include "cache.h"
 
+/*
+ * Do not use this for inspecting *tracked* content.  When path is a
+ * symlink to a directory, we do not want to say it is a directory when
+ * dealing with tracked content in the working tree.
+ */
+int is_directory(const char *path)
+{
+	struct stat st;
+	return (!stat(path, &st) && S_ISDIR(st.st_mode));
+}
+
 /* We allow "recursive" symbolic links. Only within reason, though. */
 #define MAXDEPTH 5
 
@@ -17,7 +28,7 @@ const char *make_absolute_path(const char *path)
 		die ("Too long path: %.*s", 60, path);
 
 	while (depth--) {
-		if (stat(buf, &st) || !S_ISDIR(st.st_mode)) {
+		if (!is_directory(buf)) {
 			char *last_slash = strrchr(buf, '/');
 			if (last_slash) {
 				*last_slash = '\0';
diff --git a/builtin-clone.c b/builtin-clone.c
index c8435295ce..a4b87904fc 100644
--- a/builtin-clone.c
+++ b/builtin-clone.c
@@ -77,7 +77,7 @@ static char *get_repo_path(const char *repo, int *is_bundle)
 	for (i = 0; i < ARRAY_SIZE(suffix); i++) {
 		const char *path;
 		path = mkpath("%s%s", repo, suffix[i]);
-		if (!stat(path, &st) && S_ISDIR(st.st_mode)) {
+		if (is_directory(path)) {
 			*is_bundle = 0;
 			return xstrdup(make_nonrelative_path(path));
 		}
@@ -140,13 +140,6 @@ static char *guess_dir_name(const char *repo, int is_bundle, int is_bare)
 	return xstrndup(start, end - start);
 }
 
-static int is_directory(const char *path)
-{
-	struct stat buf;
-
-	return !stat(path, &buf) && S_ISDIR(buf.st_mode);
-}
-
 static void strip_trailing_slashes(char *dir)
 {
 	char *end = dir + strlen(dir);
diff --git a/cache.h b/cache.h
index de8c2b6266..ce1f63090d 100644
--- a/cache.h
+++ b/cache.h
@@ -533,6 +533,7 @@ static inline int is_absolute_path(const char *path)
 {
 	return path[0] == '/' || has_dos_drive_prefix(path);
 }
+int is_directory(const char *);
 const char *make_absolute_path(const char *path);
 const char *make_nonrelative_path(const char *path);
 const char *make_relative_path(const char *abs, const char *base);
diff --git a/daemon.c b/daemon.c
index c315932ced..ab7a273859 100644
--- a/daemon.c
+++ b/daemon.c
@@ -1115,13 +1115,9 @@ int main(int argc, char **argv)
 	if (strict_paths && (!ok_paths || !*ok_paths))
 		die("option --strict-paths requires a whitelist");
 
-	if (base_path) {
-		struct stat st;
-
-		if (stat(base_path, &st) || !S_ISDIR(st.st_mode))
-			die("base-path '%s' does not exist or "
-			    "is not a directory", base_path);
-	}
+	if (base_path && !is_directory(base_path))
+		die("base-path '%s' does not exist or is not a directory",
+		    base_path);
 
 	if (inetd_mode) {
 		struct sockaddr_storage ss;
diff --git a/rerere.c b/rerere.c
index 323e493daf..c38886b22a 100644
--- a/rerere.c
+++ b/rerere.c
@@ -319,7 +319,6 @@ static int git_rerere_config(const char *var, const char *value, void *cb)
 
 static int is_rerere_enabled(void)
 {
-	struct stat st;
 	const char *rr_cache;
 	int rr_cache_exists;
 
@@ -327,7 +326,7 @@ static int is_rerere_enabled(void)
 		return 0;
 
 	rr_cache = git_path("rr-cache");
-	rr_cache_exists = !stat(rr_cache, &st) && S_ISDIR(st.st_mode);
+	rr_cache_exists = is_directory(rr_cache);
 	if (rerere_enabled < 0)
 		return rr_cache_exists;
 
diff --git a/sha1_file.c b/sha1_file.c
index 9ee1ed16ad..ae550e89c0 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -250,7 +250,6 @@ static void read_info_alternates(const char * alternates, int depth);
  */
 static int link_alt_odb_entry(const char * entry, int len, const char * relative_base, int depth)
 {
-	struct stat st;
 	const char *objdir = get_object_directory();
 	struct alternate_object_database *ent;
 	struct alternate_object_database *alt;
@@ -281,7 +280,7 @@ static int link_alt_odb_entry(const char * entry, int len, const char * relative
 	ent->base[pfxlen] = ent->base[entlen-1] = 0;
 
 	/* Detect cases where alternate disappeared */
-	if (stat(ent->base, &st) || !S_ISDIR(st.st_mode)) {
+	if (!is_directory(ent->base)) {
 		error("object directory %s does not exist; "
 		      "check .git/objects/info/alternates.",
 		      ent->base);

From be5908aed35d1c129f1ea38913b230ee1927361b Mon Sep 17 00:00:00 2001
From: Junio C Hamano <gitster@pobox.com>
Date: Tue, 9 Sep 2008 01:27:08 -0700
Subject: [PATCH 2/4] receive-pack: make it a builtin

It is a good thing to do in general, but more importantly, transport
routines can only be used by built-ins, which is what I'll be adding next.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 Makefile                                 | 2 +-
 receive-pack.c => builtin-receive-pack.c | 6 +++---
 builtin.h                                | 1 +
 git.c                                    | 1 +
 4 files changed, 6 insertions(+), 4 deletions(-)
 rename receive-pack.c => builtin-receive-pack.c (99%)

diff --git a/Makefile b/Makefile
index f4c31c8714..f9c54ffd2f 100644
--- a/Makefile
+++ b/Makefile
@@ -294,7 +294,6 @@ PROGRAMS += git-mktag$X
 PROGRAMS += git-mktree$X
 PROGRAMS += git-pack-redundant$X
 PROGRAMS += git-patch-id$X
-PROGRAMS += git-receive-pack$X
 PROGRAMS += git-send-pack$X
 PROGRAMS += git-shell$X
 PROGRAMS += git-show-index$X
@@ -546,6 +545,7 @@ BUILTIN_OBJS += builtin-prune-packed.o
 BUILTIN_OBJS += builtin-prune.o
 BUILTIN_OBJS += builtin-push.o
 BUILTIN_OBJS += builtin-read-tree.o
+BUILTIN_OBJS += builtin-receive-pack.o
 BUILTIN_OBJS += builtin-reflog.o
 BUILTIN_OBJS += builtin-remote.o
 BUILTIN_OBJS += builtin-rerere.o
diff --git a/receive-pack.c b/builtin-receive-pack.c
similarity index 99%
rename from receive-pack.c
rename to builtin-receive-pack.c
index b81678a970..6d6027ead1 100644
--- a/receive-pack.c
+++ b/builtin-receive-pack.c
@@ -462,14 +462,14 @@ static int delete_only(struct command *cmd)
 	return 1;
 }
 
-int main(int argc, char **argv)
+int cmd_receive_pack(int argc, const char **argv, const char *prefix)
 {
 	int i;
 	char *dir = NULL;
 
 	argv++;
 	for (i = 1; i < argc; i++) {
-		char *arg = *argv++;
+		const char *arg = *argv++;
 
 		if (*arg == '-') {
 			/* Do flag handling here */
@@ -477,7 +477,7 @@ int main(int argc, char **argv)
 		}
 		if (dir)
 			usage(receive_pack_usage);
-		dir = arg;
+		dir = xstrdup(arg);
 	}
 	if (!dir)
 		usage(receive_pack_usage);
diff --git a/builtin.h b/builtin.h
index e67cb2090e..5d7cdca70c 100644
--- a/builtin.h
+++ b/builtin.h
@@ -78,6 +78,7 @@ extern int cmd_prune(int argc, const char **argv, const char *prefix);
 extern int cmd_prune_packed(int argc, const char **argv, const char *prefix);
 extern int cmd_push(int argc, const char **argv, const char *prefix);
 extern int cmd_read_tree(int argc, const char **argv, const char *prefix);
+extern int cmd_receive_pack(int argc, const char **argv, const char *prefix);
 extern int cmd_reflog(int argc, const char **argv, const char *prefix);
 extern int cmd_remote(int argc, const char **argv, const char *prefix);
 extern int cmd_config(int argc, const char **argv, const char *prefix);
diff --git a/git.c b/git.c
index adf7352409..2f5b4d72ee 100644
--- a/git.c
+++ b/git.c
@@ -328,6 +328,7 @@ static void handle_internal_command(int argc, const char **argv)
 		{ "prune-packed", cmd_prune_packed, RUN_SETUP },
 		{ "push", cmd_push, RUN_SETUP },
 		{ "read-tree", cmd_read_tree, RUN_SETUP },
+		{ "receive-pack", cmd_receive_pack },
 		{ "reflog", cmd_reflog, RUN_SETUP },
 		{ "remote", cmd_remote, RUN_SETUP },
 		{ "repo-config", cmd_config },

From 40c155ff14c8b313d408f2e51a55c881ce082e4e Mon Sep 17 00:00:00 2001
From: Junio C Hamano <gitster@pobox.com>
Date: Tue, 9 Sep 2008 01:27:09 -0700
Subject: [PATCH 3/4] push: prepare sender to receive extended ref information
 from the receiver

"git push" enhancement allows the receiving end to report not only its own
refs but refs in repositories it borrows from via the alternate object
store mechanism.  By telling the sender that objects reachable from these
extra refs are already complete in the receiving end, the number of
objects that need to be transfered can be cut down.

These entries are sent over the wire with string ".have", instead of the
actual names of the refs.  This string was chosen so that they are ignored
by older programs at the sending end.  If we sent some random but valid
looking refnames for these entries, "matching refs" rule (triggered when
running "git push" without explicit refspecs, where the sender learns what
refs the receiver has, and updates only the ones with the names of the
refs the sender also has) and "delete missing" rule (triggered when "git
push --mirror" is used, where the sender tells the receiver to delete the
refs it itself does not have) would try to update/delete them, which is
not what we want.

This prepares the send-pack (and "push" that runs native protocol) to
accept extended existing ref information and make use of it.  The ".have"
entries are excluded from ref matching rules, and are exempt from deletion
rule while pushing with --mirror option, but are still used for pack
generation purposes by providing more "bottom" range commits.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 builtin-fetch-pack.c |  2 +-
 builtin-send-pack.c  | 21 ++++++++++++++++-----
 cache.h              |  6 +++++-
 connect.c            | 16 +++++++++++++++-
 transport.c          |  4 ++--
 5 files changed, 39 insertions(+), 10 deletions(-)

diff --git a/builtin-fetch-pack.c b/builtin-fetch-pack.c
index 459c6f0da3..e0c25615ef 100644
--- a/builtin-fetch-pack.c
+++ b/builtin-fetch-pack.c
@@ -735,7 +735,7 @@ int cmd_fetch_pack(int argc, const char **argv, const char *prefix)
 	conn = git_connect(fd, (char *)dest, args.uploadpack,
 			   args.verbose ? CONNECT_VERBOSE : 0);
 	if (conn) {
-		get_remote_heads(fd[0], &ref, 0, NULL, 0);
+		get_remote_heads(fd[0], &ref, 0, NULL, 0, NULL);
 
 		ref = fetch_pack(&args, fd, conn, ref, dest, nr_heads, heads, NULL);
 		close(fd[0]);
diff --git a/builtin-send-pack.c b/builtin-send-pack.c
index 7588d22885..b3c22f6a4a 100644
--- a/builtin-send-pack.c
+++ b/builtin-send-pack.c
@@ -18,7 +18,7 @@ static struct send_pack_args args = {
 /*
  * Make a pack stream and spit it out into file descriptor fd
  */
-static int pack_objects(int fd, struct ref *refs)
+static int pack_objects(int fd, struct ref *refs, struct extra_have_objects *extra)
 {
 	/*
 	 * The child becomes pack-objects --revs; we feed
@@ -34,6 +34,8 @@ static int pack_objects(int fd, struct ref *refs)
 		NULL,
 	};
 	struct child_process po;
+	int i;
+	char buf[42];
 
 	if (args.use_thin_pack)
 		argv[4] = "--thin";
@@ -49,9 +51,15 @@ static int pack_objects(int fd, struct ref *refs)
 	 * We feed the pack-objects we just spawned with revision
 	 * parameters by writing to the pipe.
 	 */
-	while (refs) {
-		char buf[42];
+	for (i = 0; i < extra->nr; i++) {
+		memcpy(buf + 1, sha1_to_hex(&extra->array[i][0]), 40);
+		buf[0] = '^';
+		buf[41] = '\n';
+		if (!write_or_whine(po.in, buf, 42, "send-pack: send refs"))
+			break;
+	}
 
+	while (refs) {
 		if (!is_null_sha1(refs->old_sha1) &&
 		    has_sha1_file(refs->old_sha1)) {
 			memcpy(buf + 1, sha1_to_hex(refs->old_sha1), 40);
@@ -381,14 +389,17 @@ static int do_send_pack(int in, int out, struct remote *remote, const char *dest
 	int expect_status_report = 0;
 	int flags = MATCH_REFS_NONE;
 	int ret;
+	struct extra_have_objects extra_have;
 
+	memset(&extra_have, 0, sizeof(extra_have));
 	if (args.send_all)
 		flags |= MATCH_REFS_ALL;
 	if (args.send_mirror)
 		flags |= MATCH_REFS_MIRROR;
 
 	/* No funny business with the matcher */
-	remote_tail = get_remote_heads(in, &remote_refs, 0, NULL, REF_NORMAL);
+	remote_tail = get_remote_heads(in, &remote_refs, 0, NULL, REF_NORMAL,
+				       &extra_have);
 	get_local_heads();
 
 	/* Does the other end support the reporting? */
@@ -496,7 +507,7 @@ static int do_send_pack(int in, int out, struct remote *remote, const char *dest
 
 	packet_flush(out);
 	if (new_refs && !args.dry_run) {
-		if (pack_objects(out, remote_refs) < 0)
+		if (pack_objects(out, remote_refs, &extra_have) < 0)
 			return -1;
 	}
 	else
diff --git a/cache.h b/cache.h
index ce1f63090d..98a742122d 100644
--- a/cache.h
+++ b/cache.h
@@ -709,7 +709,11 @@ extern struct child_process *git_connect(int fd[2], const char *url, const char
 extern int finish_connect(struct child_process *conn);
 extern int path_match(const char *path, int nr, char **match);
 extern int get_ack(int fd, unsigned char *result_sha1);
-extern struct ref **get_remote_heads(int in, struct ref **list, int nr_match, char **match, unsigned int flags);
+struct extra_have_objects {
+	int nr, alloc;
+	unsigned char (*array)[20];
+};
+extern struct ref **get_remote_heads(int in, struct ref **list, int nr_match, char **match, unsigned int flags, struct extra_have_objects *);
 extern int server_supports(const char *feature);
 
 extern struct packed_git *parse_pack_index(unsigned char *sha1);
diff --git a/connect.c b/connect.c
index dd96f8e043..67d2cd86a8 100644
--- a/connect.c
+++ b/connect.c
@@ -41,12 +41,20 @@ int check_ref_type(const struct ref *ref, int flags)
 	return check_ref(ref->name, strlen(ref->name), flags);
 }
 
+static void add_extra_have(struct extra_have_objects *extra, unsigned char *sha1)
+{
+	ALLOC_GROW(extra->array, extra->nr + 1, extra->alloc);
+	hashcpy(&(extra->array[extra->nr][0]), sha1);
+	extra->nr++;
+}
+
 /*
  * Read all the refs from the other end
  */
 struct ref **get_remote_heads(int in, struct ref **list,
 			      int nr_match, char **match,
-			      unsigned int flags)
+			      unsigned int flags,
+			      struct extra_have_objects *extra_have)
 {
 	*list = NULL;
 	for (;;) {
@@ -72,6 +80,12 @@ struct ref **get_remote_heads(int in, struct ref **list,
 			server_capabilities = xstrdup(name + name_len + 1);
 		}
 
+		if (extra_have &&
+		    name_len == 5 && !memcmp(".have", name, 5)) {
+			add_extra_have(extra_have, old_sha1);
+			continue;
+		}
+
 		if (!check_ref(name, name_len, flags))
 			continue;
 		if (nr_match && !path_match(name, nr_match, match))
diff --git a/transport.c b/transport.c
index 71433d9997..f7db5d9110 100644
--- a/transport.c
+++ b/transport.c
@@ -619,7 +619,7 @@ static struct ref *get_refs_via_connect(struct transport *transport)
 	struct ref *refs;
 
 	connect_setup(transport);
-	get_remote_heads(data->fd[0], &refs, 0, NULL, 0);
+	get_remote_heads(data->fd[0], &refs, 0, NULL, 0, NULL);
 
 	return refs;
 }
@@ -652,7 +652,7 @@ static int fetch_refs_via_pack(struct transport *transport,
 
 	if (!data->conn) {
 		connect_setup(transport);
-		get_remote_heads(data->fd[0], &refs_tmp, 0, NULL, 0);
+		get_remote_heads(data->fd[0], &refs_tmp, 0, NULL, 0, NULL);
 	}
 
 	refs = fetch_pack(&args, data->fd, data->conn,

From d79796bcf05b89774671a75b3285000c43129823 Mon Sep 17 00:00:00 2001
From: Junio C Hamano <gitster@pobox.com>
Date: Tue, 9 Sep 2008 01:27:10 -0700
Subject: [PATCH 4/4] push: receiver end advertises refs from alternate
 repositories

Earlier, when pushing into a repository that borrows from alternate object
stores, we followed the longstanding design decision not to trust refs in
the alternate repository that houses the object store we are borrowing
from.  If your public repository is borrowing from Linus's public
repository, you pushed into it long time ago, and now when you try to push
your updated history that is in sync with more recent history from Linus,
you will end up sending not just your own development, but also the
changes you acquired through Linus's tree, even though the objects needed
for the latter already exists at the receiving end.  This is because the
receiving end does not advertise that the objects only reachable from the
borrowed repository (i.e. Linus's) are already available there.

This solves the issue by making the receiving end advertise refs from
borrowed repositories.  They are not sent with their true names but with a
phoney name ".have" to make sure that the old senders will safely ignore
them (otherwise, the old senders will misbehave, trying to push matching
refs, and mirror push that deletes refs that only exist at the receiving
end).

Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 builtin-receive-pack.c | 38 ++++++++++++++++++++++++++++++++++++++
 cache.h                |  2 ++
 sha1_file.c            | 10 ++++++++++
 3 files changed, 50 insertions(+)

diff --git a/builtin-receive-pack.c b/builtin-receive-pack.c
index 6d6027ead1..45e3cd90fd 100644
--- a/builtin-receive-pack.c
+++ b/builtin-receive-pack.c
@@ -6,6 +6,8 @@
 #include "exec_cmd.h"
 #include "commit.h"
 #include "object.h"
+#include "remote.h"
+#include "transport.h"
 
 static const char receive_pack_usage[] = "git-receive-pack <git-dir>";
 
@@ -462,6 +464,40 @@ static int delete_only(struct command *cmd)
 	return 1;
 }
 
+static int add_refs_from_alternate(struct alternate_object_database *e, void *unused)
+{
+	char *other = xstrdup(make_absolute_path(e->base));
+	size_t len = strlen(other);
+	struct remote *remote;
+	struct transport *transport;
+	const struct ref *extra;
+
+	while (other[len-1] == '/')
+		other[--len] = '\0';
+	if (len < 8 || memcmp(other + len - 8, "/objects", 8))
+		return 0;
+	/* Is this a git repository with refs? */
+	memcpy(other + len - 8, "/refs", 6);
+	if (!is_directory(other))
+		return 0;
+	other[len - 8] = '\0';
+	remote = remote_get(other);
+	transport = transport_get(remote, other);
+	for (extra = transport_get_remote_refs(transport);
+	     extra;
+	     extra = extra->next) {
+		add_extra_ref(".have", extra->old_sha1, 0);
+	}
+	transport_disconnect(transport);
+	free(other);
+	return 0;
+}
+
+static void add_alternate_refs(void)
+{
+	foreach_alt_odb(add_refs_from_alternate, NULL);
+}
+
 int cmd_receive_pack(int argc, const char **argv, const char *prefix)
 {
 	int i;
@@ -497,7 +533,9 @@ int cmd_receive_pack(int argc, const char **argv, const char *prefix)
 	else if (0 <= receive_unpack_limit)
 		unpack_limit = receive_unpack_limit;
 
+	add_alternate_refs();
 	write_head_info();
+	clear_extra_refs();
 
 	/* EOF */
 	packet_flush(1);
diff --git a/cache.h b/cache.h
index 98a742122d..99af83a047 100644
--- a/cache.h
+++ b/cache.h
@@ -641,6 +641,8 @@ extern struct alternate_object_database {
 } *alt_odb_list;
 extern void prepare_alt_odb(void);
 extern void add_to_alternates_file(const char *reference);
+typedef int alt_odb_fn(struct alternate_object_database *, void *);
+extern void foreach_alt_odb(alt_odb_fn, void*);
 
 struct pack_window {
 	struct pack_window *next;
diff --git a/sha1_file.c b/sha1_file.c
index ae550e89c0..12be17b5da 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -393,6 +393,16 @@ void add_to_alternates_file(const char *reference)
 		link_alt_odb_entries(alt, alt + strlen(alt), '\n', NULL, 0);
 }
 
+void foreach_alt_odb(alt_odb_fn fn, void *cb)
+{
+	struct alternate_object_database *ent;
+
+	prepare_alt_odb();
+	for (ent = alt_odb_list; ent; ent = ent->next)
+		if (fn(ent, cb))
+			return;
+}
+
 void prepare_alt_odb(void)
 {
 	const char *alt;