From 261d1ac0e3a189f10a8ee42fbf68b770e4363d4f Mon Sep 17 00:00:00 2001
From: Ori Bernstein <ori@eigenstate.org>
Date: Sat, 16 Apr 2022 23:52:10 +0000
Subject: [PATCH] git/pull: fetch all branches (please test)

there was a diff that went in a while ago to improve
this, but it got backed out because it encounters a
bug in upstream git -- the spec says that a single
ACK should be sent when not using multi-ack modes,
but they send back multiple ones.

This commit brings back the functionality, and works
around the upstream git bug in two different ways.

First, it skips the packets up until it finds the
start of a pack header.

Second, it deduplicates the want messages, which
is what seems to trigger the duplicate ACKs that
cause us trouble.
---
 sys/src/cmd/git/fetch.c | 38 +++++++++++++++++++++++++++++++++-----
 sys/src/cmd/git/pull    |  5 +----
 2 files changed, 34 insertions(+), 9 deletions(-)

diff --git a/sys/src/cmd/git/fetch.c b/sys/src/cmd/git/fetch.c
index d162ac7da..95dfe106e 100644
--- a/sys/src/cmd/git/fetch.c
+++ b/sys/src/cmd/git/fetch.c
@@ -180,12 +180,13 @@ fail(char *pack, char *idx, char *msg, ...)
 int
 fetchpack(Conn *c)
 {
-	char buf[Pktmax], *sp[3];
+	char buf[Pktmax], *sp[3], *ep;
 	char *packtmp, *idxtmp, **ref;
 	Hash h, *have, *want;
 	int nref, refsz, first;
-	int i, n, req, pfd;
+	int i, n, l, req, pfd;
 	vlong packsz;
+	Objset hadobj;
 	Object *o;
 
 	nref = 0;
@@ -246,13 +247,19 @@ fetchpack(Conn *c)
 		req = 1;
 	}
 	flushpkt(c);
+	osinit(&hadobj);
 	for(i = 0; i < nref; i++){
-		if(hasheq(&have[i], &Zhash))
+		if(hasheq(&have[i], &Zhash) || oshas(&hadobj, have[i]))
 			continue;
+		if((o = readobject(have[i])) == nil)
+			sysfatal("missing object we should have: %H", have[i]);
+		osadd(&hadobj, o);
+		unref(o);	
 		n = snprint(buf, sizeof(buf), "have %H\n", have[i]);
 		if(writepkt(c, buf, n + 1) == -1)
 			sysfatal("could not send have for %H", have[i]);
 	}
+	osclear(&hadobj);
 	if(!req)
 		flushpkt(c);
 
@@ -260,7 +267,7 @@ fetchpack(Conn *c)
 	if(writepkt(c, buf, n) == -1)
 		sysfatal("write: %r");
 	if(!req)
-		return 0;
+		goto showrefs;
 	if(readphase(c) == -1)
 		sysfatal("read: %r");
 	if((n = readpkt(c, buf, sizeof(buf))) == -1)
@@ -277,7 +284,28 @@ fetchpack(Conn *c)
 		sysfatal("could not create %s: %r", packtmp);
 
 	fprint(2, "fetching...\n");
-	packsz = 0;
+	/*
+	 * Work around torvalds git bug: we get duplicate have lines
+	 * somtimes, even though the protocol is supposed to start the
+	 * pack file immediately.
+	 *
+	 * Skip ahead until we read 'PACK' off the wire
+	 */
+	while(1){
+		if(readn(c->rfd, buf, 4) != 4)
+			sysfatal("fetch packfile: short read");
+		buf[4] = 0;
+		if(strncmp(buf, "PACK", 4) == 0)
+			break;
+		l = strtol(buf, &ep, 16);
+		if(l == 0 || ep != buf + 4)
+			sysfatal("fetch packfile: junk pktline");
+		if(readn(c->rfd, buf, l) != l)
+			sysfatal("fetch packfile: short read");
+	}
+	if(write(pfd, "PACK", 4) != 4)
+		sysfatal("write pack header: %r");
+	packsz = 4;
 	while(1){
 		n = read(c->rfd, buf, sizeof buf);
 		if(n == 0)
diff --git a/sys/src/cmd/git/pull b/sys/src/cmd/git/pull
index 189323f97..4b84a9f8a 100755
--- a/sys/src/cmd/git/pull
+++ b/sys/src/cmd/git/pull
@@ -7,13 +7,10 @@ fn update{
 	upstream=$2
 	url=$3
 	dir=$4
-	bflag=()
 	dflag=()
-	if(! ~ $#branch 0)
-		bflag=(-b $branch)
 	if(! ~ $#debug 0)
 		dflag='-d'
-	{git/fetch $dflag $bflag -u $upstream $url >[2=3] || die $status} | awk '
+	{git/fetch $dflag -u $upstream $url >[2=3] || die $status} | awk '
 	/^remote/{
 		if($2=="HEAD")
 			next