blob: e92bda96c6b1904e9a059715166b951f65f3fed0 [file] [log] [blame]
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">
<head>
<meta http-equiv="Content-Type" content="application/xhtml+xml; charset=UTF-8" />
<meta name="generator" content="AsciiDoc 8.6.10" />
<title>How to recover an object from scratch</title>
<style type="text/css">
/* Shared CSS for AsciiDoc xhtml11 and html5 backends */
/* Default font. */
body {
font-family: Georgia,serif;
}
/* Title font. */
h1, h2, h3, h4, h5, h6,
div.title, caption.title,
thead, p.table.header,
#toctitle,
#author, #revnumber, #revdate, #revremark,
#footer {
font-family: Arial,Helvetica,sans-serif;
}
body {
margin: 1em 5% 1em 5%;
}
a {
color: blue;
text-decoration: underline;
}
a:visited {
color: fuchsia;
}
em {
font-style: italic;
color: navy;
}
strong {
font-weight: bold;
color: #083194;
}
h1, h2, h3, h4, h5, h6 {
color: #527bbd;
margin-top: 1.2em;
margin-bottom: 0.5em;
line-height: 1.3;
}
h1, h2, h3 {
border-bottom: 2px solid silver;
}
h2 {
padding-top: 0.5em;
}
h3 {
float: left;
}
h3 + * {
clear: left;
}
h5 {
font-size: 1.0em;
}
div.sectionbody {
margin-left: 0;
}
hr {
border: 1px solid silver;
}
p {
margin-top: 0.5em;
margin-bottom: 0.5em;
}
ul, ol, li > p {
margin-top: 0;
}
ul > li { color: #aaa; }
ul > li > * { color: black; }
.monospaced, code, pre {
font-family: "Courier New", Courier, monospace;
font-size: inherit;
color: navy;
padding: 0;
margin: 0;
}
pre {
white-space: pre-wrap;
}
#author {
color: #527bbd;
font-weight: bold;
font-size: 1.1em;
}
#email {
}
#revnumber, #revdate, #revremark {
}
#footer {
font-size: small;
border-top: 2px solid silver;
padding-top: 0.5em;
margin-top: 4.0em;
}
#footer-text {
float: left;
padding-bottom: 0.5em;
}
#footer-badges {
float: right;
padding-bottom: 0.5em;
}
#preamble {
margin-top: 1.5em;
margin-bottom: 1.5em;
}
div.imageblock, div.exampleblock, div.verseblock,
div.quoteblock, div.literalblock, div.listingblock, div.sidebarblock,
div.admonitionblock {
margin-top: 1.0em;
margin-bottom: 1.5em;
}
div.admonitionblock {
margin-top: 2.0em;
margin-bottom: 2.0em;
margin-right: 10%;
color: #606060;
}
div.content { /* Block element content. */
padding: 0;
}
/* Block element titles. */
div.title, caption.title {
color: #527bbd;
font-weight: bold;
text-align: left;
margin-top: 1.0em;
margin-bottom: 0.5em;
}
div.title + * {
margin-top: 0;
}
td div.title:first-child {
margin-top: 0.0em;
}
div.content div.title:first-child {
margin-top: 0.0em;
}
div.content + div.title {
margin-top: 0.0em;
}
div.sidebarblock > div.content {
background: #ffffee;
border: 1px solid #dddddd;
border-left: 4px solid #f0f0f0;
padding: 0.5em;
}
div.listingblock > div.content {
border: 1px solid #dddddd;
border-left: 5px solid #f0f0f0;
background: #f8f8f8;
padding: 0.5em;
}
div.quoteblock, div.verseblock {
padding-left: 1.0em;
margin-left: 1.0em;
margin-right: 10%;
border-left: 5px solid #f0f0f0;
color: #888;
}
div.quoteblock > div.attribution {
padding-top: 0.5em;
text-align: right;
}
div.verseblock > pre.content {
font-family: inherit;
font-size: inherit;
}
div.verseblock > div.attribution {
padding-top: 0.75em;
text-align: left;
}
/* DEPRECATED: Pre version 8.2.7 verse style literal block. */
div.verseblock + div.attribution {
text-align: left;
}
div.admonitionblock .icon {
vertical-align: top;
font-size: 1.1em;
font-weight: bold;
text-decoration: underline;
color: #527bbd;
padding-right: 0.5em;
}
div.admonitionblock td.content {
padding-left: 0.5em;
border-left: 3px solid #dddddd;
}
div.exampleblock > div.content {
border-left: 3px solid #dddddd;
padding-left: 0.5em;
}
div.imageblock div.content { padding-left: 0; }
span.image img { border-style: none; vertical-align: text-bottom; }
a.image:visited { color: white; }
dl {
margin-top: 0.8em;
margin-bottom: 0.8em;
}
dt {
margin-top: 0.5em;
margin-bottom: 0;
font-style: normal;
color: navy;
}
dd > *:first-child {
margin-top: 0.1em;
}
ul, ol {
list-style-position: outside;
}
ol.arabic {
list-style-type: decimal;
}
ol.loweralpha {
list-style-type: lower-alpha;
}
ol.upperalpha {
list-style-type: upper-alpha;
}
ol.lowerroman {
list-style-type: lower-roman;
}
ol.upperroman {
list-style-type: upper-roman;
}
div.compact ul, div.compact ol,
div.compact p, div.compact p,
div.compact div, div.compact div {
margin-top: 0.1em;
margin-bottom: 0.1em;
}
tfoot {
font-weight: bold;
}
td > div.verse {
white-space: pre;
}
div.hdlist {
margin-top: 0.8em;
margin-bottom: 0.8em;
}
div.hdlist tr {
padding-bottom: 15px;
}
dt.hdlist1.strong, td.hdlist1.strong {
font-weight: bold;
}
td.hdlist1 {
vertical-align: top;
font-style: normal;
padding-right: 0.8em;
color: navy;
}
td.hdlist2 {
vertical-align: top;
}
div.hdlist.compact tr {
margin: 0;
padding-bottom: 0;
}
.comment {
background: yellow;
}
.footnote, .footnoteref {
font-size: 0.8em;
}
span.footnote, span.footnoteref {
vertical-align: super;
}
#footnotes {
margin: 20px 0 20px 0;
padding: 7px 0 0 0;
}
#footnotes div.footnote {
margin: 0 0 5px 0;
}
#footnotes hr {
border: none;
border-top: 1px solid silver;
height: 1px;
text-align: left;
margin-left: 0;
width: 20%;
min-width: 100px;
}
div.colist td {
padding-right: 0.5em;
padding-bottom: 0.3em;
vertical-align: top;
}
div.colist td img {
margin-top: 0.3em;
}
@media print {
#footer-badges { display: none; }
}
#toc {
margin-bottom: 2.5em;
}
#toctitle {
color: #527bbd;
font-size: 1.1em;
font-weight: bold;
margin-top: 1.0em;
margin-bottom: 0.1em;
}
div.toclevel0, div.toclevel1, div.toclevel2, div.toclevel3, div.toclevel4 {
margin-top: 0;
margin-bottom: 0;
}
div.toclevel2 {
margin-left: 2em;
font-size: 0.9em;
}
div.toclevel3 {
margin-left: 4em;
font-size: 0.9em;
}
div.toclevel4 {
margin-left: 6em;
font-size: 0.9em;
}
span.aqua { color: aqua; }
span.black { color: black; }
span.blue { color: blue; }
span.fuchsia { color: fuchsia; }
span.gray { color: gray; }
span.green { color: green; }
span.lime { color: lime; }
span.maroon { color: maroon; }
span.navy { color: navy; }
span.olive { color: olive; }
span.purple { color: purple; }
span.red { color: red; }
span.silver { color: silver; }
span.teal { color: teal; }
span.white { color: white; }
span.yellow { color: yellow; }
span.aqua-background { background: aqua; }
span.black-background { background: black; }
span.blue-background { background: blue; }
span.fuchsia-background { background: fuchsia; }
span.gray-background { background: gray; }
span.green-background { background: green; }
span.lime-background { background: lime; }
span.maroon-background { background: maroon; }
span.navy-background { background: navy; }
span.olive-background { background: olive; }
span.purple-background { background: purple; }
span.red-background { background: red; }
span.silver-background { background: silver; }
span.teal-background { background: teal; }
span.white-background { background: white; }
span.yellow-background { background: yellow; }
span.big { font-size: 2em; }
span.small { font-size: 0.6em; }
span.underline { text-decoration: underline; }
span.overline { text-decoration: overline; }
span.line-through { text-decoration: line-through; }
div.unbreakable { page-break-inside: avoid; }
/*
* xhtml11 specific
*
* */
div.tableblock {
margin-top: 1.0em;
margin-bottom: 1.5em;
}
div.tableblock > table {
border: 3px solid #527bbd;
}
thead, p.table.header {
font-weight: bold;
color: #527bbd;
}
p.table {
margin-top: 0;
}
/* Because the table frame attribute is overriden by CSS in most browsers. */
div.tableblock > table[frame="void"] {
border-style: none;
}
div.tableblock > table[frame="hsides"] {
border-left-style: none;
border-right-style: none;
}
div.tableblock > table[frame="vsides"] {
border-top-style: none;
border-bottom-style: none;
}
/*
* html5 specific
*
* */
table.tableblock {
margin-top: 1.0em;
margin-bottom: 1.5em;
}
thead, p.tableblock.header {
font-weight: bold;
color: #527bbd;
}
p.tableblock {
margin-top: 0;
}
table.tableblock {
border-width: 3px;
border-spacing: 0px;
border-style: solid;
border-color: #527bbd;
border-collapse: collapse;
}
th.tableblock, td.tableblock {
border-width: 1px;
padding: 4px;
border-style: solid;
border-color: #527bbd;
}
table.tableblock.frame-topbot {
border-left-style: hidden;
border-right-style: hidden;
}
table.tableblock.frame-sides {
border-top-style: hidden;
border-bottom-style: hidden;
}
table.tableblock.frame-none {
border-style: hidden;
}
th.tableblock.halign-left, td.tableblock.halign-left {
text-align: left;
}
th.tableblock.halign-center, td.tableblock.halign-center {
text-align: center;
}
th.tableblock.halign-right, td.tableblock.halign-right {
text-align: right;
}
th.tableblock.valign-top, td.tableblock.valign-top {
vertical-align: top;
}
th.tableblock.valign-middle, td.tableblock.valign-middle {
vertical-align: middle;
}
th.tableblock.valign-bottom, td.tableblock.valign-bottom {
vertical-align: bottom;
}
/*
* manpage specific
*
* */
body.manpage h1 {
padding-top: 0.5em;
padding-bottom: 0.5em;
border-top: 2px solid silver;
border-bottom: 2px solid silver;
}
body.manpage h2 {
border-style: none;
}
body.manpage div.sectionbody {
margin-left: 3em;
}
@media print {
body.manpage div#toc { display: none; }
}
</style>
<script type="text/javascript">
/*<![CDATA[*/
var asciidoc = { // Namespace.
/////////////////////////////////////////////////////////////////////
// Table Of Contents generator
/////////////////////////////////////////////////////////////////////
/* Author: Mihai Bazon, September 2002
* http://students.infoiasi.ro/~mishoo
*
* Table Of Content generator
* Version: 0.4
*
* Feel free to use this script under the terms of the GNU General Public
* License, as long as you do not remove or alter this notice.
*/
/* modified by Troy D. Hanson, September 2006. License: GPL */
/* modified by Stuart Rackham, 2006, 2009. License: GPL */
// toclevels = 1..4.
toc: function (toclevels) {
function getText(el) {
var text = "";
for (var i = el.firstChild; i != null; i = i.nextSibling) {
if (i.nodeType == 3 /* Node.TEXT_NODE */) // IE doesn't speak constants.
text += i.data;
else if (i.firstChild != null)
text += getText(i);
}
return text;
}
function TocEntry(el, text, toclevel) {
this.element = el;
this.text = text;
this.toclevel = toclevel;
}
function tocEntries(el, toclevels) {
var result = new Array;
var re = new RegExp('[hH]([1-'+(toclevels+1)+'])');
// Function that scans the DOM tree for header elements (the DOM2
// nodeIterator API would be a better technique but not supported by all
// browsers).
var iterate = function (el) {
for (var i = el.firstChild; i != null; i = i.nextSibling) {
if (i.nodeType == 1 /* Node.ELEMENT_NODE */) {
var mo = re.exec(i.tagName);
if (mo && (i.getAttribute("class") || i.getAttribute("className")) != "float") {
result[result.length] = new TocEntry(i, getText(i), mo[1]-1);
}
iterate(i);
}
}
}
iterate(el);
return result;
}
var toc = document.getElementById("toc");
if (!toc) {
return;
}
// Delete existing TOC entries in case we're reloading the TOC.
var tocEntriesToRemove = [];
var i;
for (i = 0; i < toc.childNodes.length; i++) {
var entry = toc.childNodes[i];
if (entry.nodeName.toLowerCase() == 'div'
&& entry.getAttribute("class")
&& entry.getAttribute("class").match(/^toclevel/))
tocEntriesToRemove.push(entry);
}
for (i = 0; i < tocEntriesToRemove.length; i++) {
toc.removeChild(tocEntriesToRemove[i]);
}
// Rebuild TOC entries.
var entries = tocEntries(document.getElementById("content"), toclevels);
for (var i = 0; i < entries.length; ++i) {
var entry = entries[i];
if (entry.element.id == "")
entry.element.id = "_toc_" + i;
var a = document.createElement("a");
a.href = "#" + entry.element.id;
a.appendChild(document.createTextNode(entry.text));
var div = document.createElement("div");
div.appendChild(a);
div.className = "toclevel" + entry.toclevel;
toc.appendChild(div);
}
if (entries.length == 0)
toc.parentNode.removeChild(toc);
},
/////////////////////////////////////////////////////////////////////
// Footnotes generator
/////////////////////////////////////////////////////////////////////
/* Based on footnote generation code from:
* http://www.brandspankingnew.net/archive/2005/07/format_footnote.html
*/
footnotes: function () {
// Delete existing footnote entries in case we're reloading the footnodes.
var i;
var noteholder = document.getElementById("footnotes");
if (!noteholder) {
return;
}
var entriesToRemove = [];
for (i = 0; i < noteholder.childNodes.length; i++) {
var entry = noteholder.childNodes[i];
if (entry.nodeName.toLowerCase() == 'div' && entry.getAttribute("class") == "footnote")
entriesToRemove.push(entry);
}
for (i = 0; i < entriesToRemove.length; i++) {
noteholder.removeChild(entriesToRemove[i]);
}
// Rebuild footnote entries.
var cont = document.getElementById("content");
var spans = cont.getElementsByTagName("span");
var refs = {};
var n = 0;
for (i=0; i<spans.length; i++) {
if (spans[i].className == "footnote") {
n++;
var note = spans[i].getAttribute("data-note");
if (!note) {
// Use [\s\S] in place of . so multi-line matches work.
// Because JavaScript has no s (dotall) regex flag.
note = spans[i].innerHTML.match(/\s*\[([\s\S]*)]\s*/)[1];
spans[i].innerHTML =
"[<a id='_footnoteref_" + n + "' href='#_footnote_" + n +
"' title='View footnote' class='footnote'>" + n + "</a>]";
spans[i].setAttribute("data-note", note);
}
noteholder.innerHTML +=
"<div class='footnote' id='_footnote_" + n + "'>" +
"<a href='#_footnoteref_" + n + "' title='Return to text'>" +
n + "</a>. " + note + "</div>";
var id =spans[i].getAttribute("id");
if (id != null) refs["#"+id] = n;
}
}
if (n == 0)
noteholder.parentNode.removeChild(noteholder);
else {
// Process footnoterefs.
for (i=0; i<spans.length; i++) {
if (spans[i].className == "footnoteref") {
var href = spans[i].getElementsByTagName("a")[0].getAttribute("href");
href = href.match(/#.*/)[0]; // Because IE return full URL.
n = refs[href];
spans[i].innerHTML =
"[<a href='#_footnote_" + n +
"' title='View footnote' class='footnote'>" + n + "</a>]";
}
}
}
},
install: function(toclevels) {
var timerId;
function reinstall() {
asciidoc.footnotes();
if (toclevels) {
asciidoc.toc(toclevels);
}
}
function reinstallAndRemoveTimer() {
clearInterval(timerId);
reinstall();
}
timerId = setInterval(reinstall, 500);
if (document.addEventListener)
document.addEventListener("DOMContentLoaded", reinstallAndRemoveTimer, false);
else
window.onload = reinstallAndRemoveTimer;
}
}
asciidoc.install();
/*]]>*/
</script>
</head>
<body class="article">
<div id="header">
<h1>How to recover an object from scratch</h1>
</div>
<div id="content">
<div id="preamble">
<div class="sectionbody">
<div class="paragraph"><p>I was recently presented with a repository with a corrupted packfile,
and was asked if the data was recoverable. This post-mortem describes
the steps I took to investigate and fix the problem. I thought others
might find the process interesting, and it might help somebody in the
same situation.</p></div>
<div class="sidebarblock">
<div class="content">
<div class="paragraph"><p>Note: In this case, no good copy of the repository was available. For
the much easier case where you can get the corrupted object from
elsewhere, see <a href="recover-corrupted-blob-object.html">this howto</a>.</p></div>
</div></div>
<div class="paragraph"><p>I started with an fsck, which found a problem with exactly one object
(I&#8217;ve used $pack and $obj below to keep the output readable, and also
because I&#8217;ll refer to them later):</p></div>
<div class="listingblock">
<div class="content">
<pre><code> $ git fsck
error: $pack SHA1 checksum mismatch
error: index CRC mismatch for object $obj from $pack at offset 51653873
error: inflate: data stream error (incorrect data check)
error: cannot unpack $obj from $pack at offset 51653873</code></pre>
</div></div>
<div class="paragraph"><p>The pack checksum failing means a byte is munged somewhere, and it is
presumably in the object mentioned (since both the index checksum and
zlib were failing).</p></div>
<div class="paragraph"><p>Reading the zlib source code, I found that "incorrect data check" means
that the adler-32 checksum at the end of the zlib data did not match the
inflated data. So stepping the data through zlib would not help, as it
did not fail until the very end, when we realize the CRC does not match.
The problematic bytes could be anywhere in the object data.</p></div>
<div class="paragraph"><p>The first thing I did was pull the broken data out of the packfile. I
needed to know how big the object was, which I found out with:</p></div>
<div class="listingblock">
<div class="content">
<pre><code> $ git show-index &lt;$idx | cut -d' ' -f1 | sort -n | grep -A1 51653873
51653873
51664736</code></pre>
</div></div>
<div class="paragraph"><p>Show-index gives us the list of objects and their offsets. We throw away
everything but the offsets, and then sort them so that our interesting
offset (which we got from the fsck output above) is followed immediately
by the offset of the next object. Now we know that the object data is
10863 bytes long, and we can grab it with:</p></div>
<div class="listingblock">
<div class="content">
<pre><code> dd if=$pack of=object bs=1 skip=51653873 count=10863</code></pre>
</div></div>
<div class="paragraph"><p>I inspected a hexdump of the data, looking for any obvious bogosity
(e.g., a 4K run of zeroes would be a good sign of filesystem
corruption). But everything looked pretty reasonable.</p></div>
<div class="paragraph"><p>Note that the "object" file isn&#8217;t fit for feeding straight to zlib; it
has the git packed object header, which is variable-length. We want to
strip that off so we can start playing with the zlib data directly. You
can either work your way through it manually (the format is described in
<a href="../technical/pack-format.html">Documentation/technical/pack-format.txt</a>),
or you can walk through it in a debugger. I did the latter, creating a
valid pack like:</p></div>
<div class="listingblock">
<div class="content">
<pre><code> # pack magic and version
printf 'PACK\0\0\0\2' &gt;tmp.pack
# pack has one object
printf '\0\0\0\1' &gt;&gt;tmp.pack
# now add our object data
cat object &gt;&gt;tmp.pack
# and then append the pack trailer
/path/to/git.git/t/helper/test-tool sha1 -b &lt;tmp.pack &gt;trailer
cat trailer &gt;&gt;tmp.pack</code></pre>
</div></div>
<div class="paragraph"><p>and then running "git index-pack tmp.pack" in the debugger (stop at
unpack_raw_entry). Doing this, I found that there were 3 bytes of header
(and the header itself had a sane type and size). So I stripped those
off with:</p></div>
<div class="listingblock">
<div class="content">
<pre><code> dd if=object of=zlib bs=1 skip=3</code></pre>
</div></div>
<div class="paragraph"><p>I ran the result through zlib&#8217;s inflate using a custom C program. And
while it did report the error, I did get the right number of output
bytes (i.e., it matched git&#8217;s size header that we decoded above). But
feeding the result back to "git hash-object" didn&#8217;t produce the same
sha1. So there were some wrong bytes, but I didn&#8217;t know which. The file
happened to be C source code, so I hoped I could notice something
obviously wrong with it, but I didn&#8217;t. I even got it to compile!</p></div>
<div class="paragraph"><p>I also tried comparing it to other versions of the same path in the
repository, hoping that there would be some part of the diff that didn&#8217;t
make sense. Unfortunately, this happened to be the only revision of this
particular file in the repository, so I had nothing to compare against.</p></div>
<div class="paragraph"><p>So I took a different approach. Working under the guess that the
corruption was limited to a single byte, I wrote a program to munge each
byte individually, and try inflating the result. Since the object was
only 10K compressed, that worked out to about 2.5M attempts, which took
a few minutes.</p></div>
<div class="paragraph"><p>The program I used is here:</p></div>
<div class="listingblock">
<div class="content">
<pre><code>#include &lt;stdio.h&gt;
#include &lt;unistd.h&gt;
#include &lt;string.h&gt;
#include &lt;signal.h&gt;
#include &lt;zlib.h&gt;
static int try_zlib(unsigned char *buf, int len)
{
/* make this absurdly large so we don't have to loop */
static unsigned char out[1024*1024];
z_stream z;
int ret;
memset(&amp;z, 0, sizeof(z));
inflateInit(&amp;z);
z.next_in = buf;
z.avail_in = len;
z.next_out = out;
z.avail_out = sizeof(out);
ret = inflate(&amp;z, 0);
inflateEnd(&amp;z);
return ret &gt;= 0;
}
/* eye candy */
static int counter = 0;
static void progress(int sig)
{
fprintf(stderr, "\r%d", counter);
alarm(1);
}
int main(void)
{
/* oversized so we can read the whole buffer in */
unsigned char buf[1024*1024];
int len;
unsigned i, j;
signal(SIGALRM, progress);
alarm(1);
len = read(0, buf, sizeof(buf));
for (i = 0; i &lt; len; i++) {
unsigned char c = buf[i];
for (j = 0; j &lt;= 0xff; j++) {
buf[i] = j;
counter++;
if (try_zlib(buf, len))
printf("i=%d, j=%x\n", i, j);
}
buf[i] = c;
}
alarm(0);
fprintf(stderr, "\n");
return 0;
}</code></pre>
</div></div>
<div class="paragraph"><p>I compiled and ran with:</p></div>
<div class="listingblock">
<div class="content">
<pre><code> gcc -Wall -Werror -O3 munge.c -o munge -lz
./munge &lt;zlib</code></pre>
</div></div>
<div class="paragraph"><p>There were a few false positives early on (if you write "no data" in the
zlib header, zlib thinks it&#8217;s just fine :) ). But I got a hit about
halfway through:</p></div>
<div class="listingblock">
<div class="content">
<pre><code> i=5642, j=c7</code></pre>
</div></div>
<div class="paragraph"><p>I let it run to completion, and got a few more hits at the end (where it
was munging the CRC to match our broken data). So there was a good
chance this middle hit was the source of the problem.</p></div>
<div class="paragraph"><p>I confirmed by tweaking the byte in a hex editor, zlib inflating the
result (no errors!), and then piping the output into "git hash-object",
which reported the sha1 of the broken object. Success!</p></div>
<div class="paragraph"><p>I fixed the packfile itself with:</p></div>
<div class="listingblock">
<div class="content">
<pre><code> chmod +w $pack
printf '\xc7' | dd of=$pack bs=1 seek=51659518 conv=notrunc
chmod -w $pack</code></pre>
</div></div>
<div class="paragraph"><p>The <code>\xc7</code> comes from the replacement byte our "munge" program found.
The offset 51659518 is derived by taking the original object offset
(51653873), adding the replacement offset found by "munge" (5642), and
then adding back in the 3 bytes of git header we stripped.</p></div>
<div class="paragraph"><p>After that, "git fsck" ran clean.</p></div>
<div class="paragraph"><p>As for the corruption itself, I was lucky that it was indeed a single
byte. In fact, it turned out to be a single bit. The byte 0xc7 was
corrupted to 0xc5. So presumably it was caused by faulty hardware, or a
cosmic ray.</p></div>
<div class="paragraph"><p>And the aborted attempt to look at the inflated output to see what was
wrong? I could have looked forever and never found it. Here&#8217;s the diff
between what the corrupted data inflates to, versus the real data:</p></div>
<div class="listingblock">
<div class="content">
<pre><code> - cp = strtok (arg, "+");
+ cp = strtok (arg, ".");</code></pre>
</div></div>
<div class="paragraph"><p>It tweaked one byte and still ended up as valid, readable C that just
happened to do something totally different! One takeaway is that on a
less unlucky day, looking at the zlib output might have actually been
helpful, as most random changes would actually break the C code.</p></div>
<div class="paragraph"><p>But more importantly, git&#8217;s hashing and checksumming noticed a problem
that easily could have gone undetected in another system. The result
still compiled, but would have caused an interesting bug (that would
have been blamed on some random commit).</p></div>
</div>
</div>
<div class="sect1">
<h2 id="_the_adventure_continues_8230">The adventure continues&#8230;</h2>
<div class="sectionbody">
<div class="paragraph"><p>I ended up doing this again! Same entity, new hardware. The assumption
at this point is that the old disk corrupted the packfile, and then the
corruption was migrated to the new hardware (because it was done by
rsync or similar, and no fsck was done at the time of migration).</p></div>
<div class="paragraph"><p>This time, the affected blob was over 20 megabytes, which was far too
large to do a brute-force on. I followed the instructions above to
create the <code>zlib</code> file. I then used the <code>inflate</code> program below to pull
the corrupted data from that. Examining that output gave me a hint about
where in the file the corruption was. But now I was working with the
file itself, not the zlib contents. So knowing the sha1 of the object
and the approximate area of the corruption, I used the <code>sha1-munge</code>
program below to brute-force the correct byte.</p></div>
<div class="paragraph"><p>Here&#8217;s the inflate program (it&#8217;s essentially <code>gunzip</code> but without the
<code>.gz</code> header processing):</p></div>
<div class="listingblock">
<div class="content">
<pre><code>#include &lt;stdio.h&gt;
#include &lt;string.h&gt;
#include &lt;zlib.h&gt;
#include &lt;stdlib.h&gt;
int main(int argc, char **argv)
{
/*
* oversized so we can read the whole buffer in;
* this could actually be switched to streaming
* to avoid any memory limitations
*/
static unsigned char buf[25 * 1024 * 1024];
static unsigned char out[25 * 1024 * 1024];
int len;
z_stream z;
int ret;
len = read(0, buf, sizeof(buf));
memset(&amp;z, 0, sizeof(z));
inflateInit(&amp;z);
z.next_in = buf;
z.avail_in = len;
z.next_out = out;
z.avail_out = sizeof(out);
ret = inflate(&amp;z, 0);
if (ret != Z_OK &amp;&amp; ret != Z_STREAM_END)
fprintf(stderr, "initial inflate failed (%d)\n", ret);
fprintf(stderr, "outputting %lu bytes", z.total_out);
fwrite(out, 1, z.total_out, stdout);
return 0;
}</code></pre>
</div></div>
<div class="paragraph"><p>And here is the <code>sha1-munge</code> program:</p></div>
<div class="listingblock">
<div class="content">
<pre><code>#include &lt;stdio.h&gt;
#include &lt;unistd.h&gt;
#include &lt;string.h&gt;
#include &lt;signal.h&gt;
#include &lt;openssl/sha.h&gt;
#include &lt;stdlib.h&gt;
/* eye candy */
static int counter = 0;
static void progress(int sig)
{
fprintf(stderr, "\r%d", counter);
alarm(1);
}
static const signed char hexval_table[256] = {
-1, -1, -1, -1, -1, -1, -1, -1, /* 00-07 */
-1, -1, -1, -1, -1, -1, -1, -1, /* 08-0f */
-1, -1, -1, -1, -1, -1, -1, -1, /* 10-17 */
-1, -1, -1, -1, -1, -1, -1, -1, /* 18-1f */
-1, -1, -1, -1, -1, -1, -1, -1, /* 20-27 */
-1, -1, -1, -1, -1, -1, -1, -1, /* 28-2f */
0, 1, 2, 3, 4, 5, 6, 7, /* 30-37 */
8, 9, -1, -1, -1, -1, -1, -1, /* 38-3f */
-1, 10, 11, 12, 13, 14, 15, -1, /* 40-47 */
-1, -1, -1, -1, -1, -1, -1, -1, /* 48-4f */
-1, -1, -1, -1, -1, -1, -1, -1, /* 50-57 */
-1, -1, -1, -1, -1, -1, -1, -1, /* 58-5f */
-1, 10, 11, 12, 13, 14, 15, -1, /* 60-67 */
-1, -1, -1, -1, -1, -1, -1, -1, /* 68-67 */
-1, -1, -1, -1, -1, -1, -1, -1, /* 70-77 */
-1, -1, -1, -1, -1, -1, -1, -1, /* 78-7f */
-1, -1, -1, -1, -1, -1, -1, -1, /* 80-87 */
-1, -1, -1, -1, -1, -1, -1, -1, /* 88-8f */
-1, -1, -1, -1, -1, -1, -1, -1, /* 90-97 */
-1, -1, -1, -1, -1, -1, -1, -1, /* 98-9f */
-1, -1, -1, -1, -1, -1, -1, -1, /* a0-a7 */
-1, -1, -1, -1, -1, -1, -1, -1, /* a8-af */
-1, -1, -1, -1, -1, -1, -1, -1, /* b0-b7 */
-1, -1, -1, -1, -1, -1, -1, -1, /* b8-bf */
-1, -1, -1, -1, -1, -1, -1, -1, /* c0-c7 */
-1, -1, -1, -1, -1, -1, -1, -1, /* c8-cf */
-1, -1, -1, -1, -1, -1, -1, -1, /* d0-d7 */
-1, -1, -1, -1, -1, -1, -1, -1, /* d8-df */
-1, -1, -1, -1, -1, -1, -1, -1, /* e0-e7 */
-1, -1, -1, -1, -1, -1, -1, -1, /* e8-ef */
-1, -1, -1, -1, -1, -1, -1, -1, /* f0-f7 */
-1, -1, -1, -1, -1, -1, -1, -1, /* f8-ff */
};
static inline unsigned int hexval(unsigned char c)
{
return hexval_table[c];
}
static int get_sha1_hex(const char *hex, unsigned char *sha1)
{
int i;
for (i = 0; i &lt; 20; i++) {
unsigned int val;
/*
* hex[1]=='\0' is caught when val is checked below,
* but if hex[0] is NUL we have to avoid reading
* past the end of the string:
*/
if (!hex[0])
return -1;
val = (hexval(hex[0]) &lt;&lt; 4) | hexval(hex[1]);
if (val &amp; ~0xff)
return -1;
*sha1++ = val;
hex += 2;
}
return 0;
}
int main(int argc, char **argv)
{
/* oversized so we can read the whole buffer in */
static unsigned char buf[25 * 1024 * 1024];
char header[32];
int header_len;
unsigned char have[20], want[20];
int start, len;
SHA_CTX orig;
unsigned i, j;
if (!argv[1] || get_sha1_hex(argv[1], want)) {
fprintf(stderr, "usage: sha1-munge &lt;sha1&gt; [start] &lt;file.in\n");
return 1;
}
if (argv[2])
start = atoi(argv[2]);
else
start = 0;
len = read(0, buf, sizeof(buf));
header_len = sprintf(header, "blob %d", len) + 1;
fprintf(stderr, "using header: %s\n", header);
/*
* We keep a running sha1 so that if you are munging
* near the end of the file, we do not have to re-sha1
* the unchanged earlier bytes
*/
SHA1_Init(&amp;orig);
SHA1_Update(&amp;orig, header, header_len);
if (start)
SHA1_Update(&amp;orig, buf, start);
signal(SIGALRM, progress);
alarm(1);
for (i = start; i &lt; len; i++) {
unsigned char c;
SHA_CTX x;
#if 0
/*
* deletion -- this would not actually work in practice,
* I think, because we've already committed to a
* particular size in the header. Ditto for addition
* below. In those cases, you'd have to do the whole
* sha1 from scratch, or possibly keep three running
* "orig" sha1 computations going.
*/
memcpy(&amp;x, &amp;orig, sizeof(x));
SHA1_Update(&amp;x, buf + i + 1, len - i - 1);
SHA1_Final(have, &amp;x);
if (!memcmp(have, want, 20))
printf("i=%d, deletion\n", i);
#endif
/*
* replacement -- note that this tries each of the 256
* possible bytes. If you suspect a single-bit flip,
* it would be much shorter to just try the 8
* bit-flipped variants.
*/
c = buf[i];
for (j = 0; j &lt;= 0xff; j++) {
buf[i] = j;
memcpy(&amp;x, &amp;orig, sizeof(x));
SHA1_Update(&amp;x, buf + i, len - i);
SHA1_Final(have, &amp;x);
if (!memcmp(have, want, 20))
printf("i=%d, j=%02x\n", i, j);
}
buf[i] = c;
#if 0
/* addition */
for (j = 0; j &lt;= 0xff; j++) {
unsigned char extra = j;
memcpy(&amp;x, &amp;orig, sizeof(x));
SHA1_Update(&amp;x, &amp;extra, 1);
SHA1_Update(&amp;x, buf + i, len - i);
SHA1_Final(have, &amp;x);
if (!memcmp(have, want, 20))
printf("i=%d, addition=%02x", i, j);
}
#endif
SHA1_Update(&amp;orig, buf + i, 1);
counter++;
}
alarm(0);
fprintf(stderr, "\r%d\n", counter);
return 0;
}</code></pre>
</div></div>
</div>
</div>
</div>
<div id="footnotes"><hr /></div>
<div id="footer">
<div id="footer-text">
Last updated
2019-02-06 23:18:40 PST
</div>
</div>
</body>
</html>