git/t/t5303-pack-corruption-resilience.sh
Shawn O. Pearce b3118bdc91 sha1_file: Fix infinite loop when pack is corrupted
Some types of corruption to a pack may confuse the deflate stream
which stores an object.  In Andy's reported case a 36 byte region
of the pack was overwritten, leading to what appeared to be a valid
deflate stream that was trying to produce a result larger than our
allocated output buffer could accept.

Z_BUF_ERROR is returned from inflate() if either the input buffer
needs more input bytes, or the output buffer has run out of space.
Previously we only considered the former case, as it meant we needed
to move the stream's input buffer to the next window in the pack.

We now abort the loop if inflate() returns Z_BUF_ERROR without
consuming the entire input buffer it was given, or has filled
the entire output buffer but has not yet returned Z_STREAM_END.
Either state is a clear indicator that this loop is not working
as expected, and should not continue.

This problem cannot occur with loose objects as we open the entire
loose object as a single buffer and treat Z_BUF_ERROR as an error.

Reported-by: Andy Isaacson <adi@hexapodia.org>
Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
Acked-by: Nicolas Pitre <nico@fluxnic.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-10-14 13:39:37 -07:00

288 lines
9.9 KiB
Bash
Executable File

#!/bin/sh
#
# Copyright (c) 2008 Nicolas Pitre
#
test_description='resilience to pack corruptions with redundant objects'
. ./test-lib.sh
# Note: the test objects are created with knowledge of their pack encoding
# to ensure good code path coverage, and to facilitate direct alteration
# later on. The assumed characteristics are:
#
# 1) blob_2 is a delta with blob_1 for base and blob_3 is a delta with blob2
# for base, such that blob_3 delta depth is 2;
#
# 2) the bulk of object data is uncompressible so the text part remains
# visible;
#
# 3) object header is always 2 bytes.
create_test_files() {
test-genrandom "foo" 2000 > file_1 &&
test-genrandom "foo" 1800 > file_2 &&
test-genrandom "foo" 1800 > file_3 &&
echo " base " >> file_1 &&
echo " delta1 " >> file_2 &&
echo " delta delta2 " >> file_3 &&
test-genrandom "bar" 150 >> file_2 &&
test-genrandom "baz" 100 >> file_3
}
create_new_pack() {
rm -rf .git &&
git init &&
blob_1=`git hash-object -t blob -w file_1` &&
blob_2=`git hash-object -t blob -w file_2` &&
blob_3=`git hash-object -t blob -w file_3` &&
pack=`printf "$blob_1\n$blob_2\n$blob_3\n" |
git pack-objects $@ .git/objects/pack/pack` &&
pack=".git/objects/pack/pack-${pack}" &&
git verify-pack -v ${pack}.pack
}
do_repack() {
pack=`printf "$blob_1\n$blob_2\n$blob_3\n" |
git pack-objects $@ .git/objects/pack/pack` &&
pack=".git/objects/pack/pack-${pack}"
}
do_corrupt_object() {
ofs=`git show-index < ${pack}.idx | grep $1 | cut -f1 -d" "` &&
ofs=$(($ofs + $2)) &&
chmod +w ${pack}.pack &&
dd of=${pack}.pack count=1 bs=1 conv=notrunc seek=$ofs &&
test_must_fail git verify-pack ${pack}.pack
}
printf '\0' > zero
test_expect_success \
'initial setup validation' \
'create_test_files &&
create_new_pack &&
git prune-packed &&
git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'create corruption in header of first object' \
'do_corrupt_object $blob_1 0 < zero &&
test_must_fail git cat-file blob $blob_1 > /dev/null &&
test_must_fail git cat-file blob $blob_2 > /dev/null &&
test_must_fail git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... but having a loose copy allows for full recovery' \
'mv ${pack}.idx tmp &&
git hash-object -t blob -w file_1 &&
mv tmp ${pack}.idx &&
git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... and loose copy of first delta allows for partial recovery' \
'git prune-packed &&
test_must_fail git cat-file blob $blob_2 > /dev/null &&
mv ${pack}.idx tmp &&
git hash-object -t blob -w file_2 &&
mv tmp ${pack}.idx &&
test_must_fail git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'create corruption in data of first object' \
'create_new_pack &&
git prune-packed &&
chmod +w ${pack}.pack &&
perl -i.bak -pe "s/ base /abcdef/" ${pack}.pack &&
test_must_fail git cat-file blob $blob_1 > /dev/null &&
test_must_fail git cat-file blob $blob_2 > /dev/null &&
test_must_fail git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... but having a loose copy allows for full recovery' \
'mv ${pack}.idx tmp &&
git hash-object -t blob -w file_1 &&
mv tmp ${pack}.idx &&
git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... and loose copy of second object allows for partial recovery' \
'git prune-packed &&
test_must_fail git cat-file blob $blob_2 > /dev/null &&
mv ${pack}.idx tmp &&
git hash-object -t blob -w file_2 &&
mv tmp ${pack}.idx &&
test_must_fail git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'create corruption in header of first delta' \
'create_new_pack &&
git prune-packed &&
do_corrupt_object $blob_2 0 < zero &&
git cat-file blob $blob_1 > /dev/null &&
test_must_fail git cat-file blob $blob_2 > /dev/null &&
test_must_fail git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... but having a loose copy allows for full recovery' \
'mv ${pack}.idx tmp &&
git hash-object -t blob -w file_2 &&
mv tmp ${pack}.idx &&
git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... and then a repack "clears" the corruption' \
'do_repack &&
git prune-packed &&
git verify-pack ${pack}.pack &&
git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'create corruption in data of first delta' \
'create_new_pack &&
git prune-packed &&
chmod +w ${pack}.pack &&
perl -i.bak -pe "s/ delta1 /abcdefgh/" ${pack}.pack &&
git cat-file blob $blob_1 > /dev/null &&
test_must_fail git cat-file blob $blob_2 > /dev/null &&
test_must_fail git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... but having a loose copy allows for full recovery' \
'mv ${pack}.idx tmp &&
git hash-object -t blob -w file_2 &&
mv tmp ${pack}.idx &&
git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... and then a repack "clears" the corruption' \
'do_repack &&
git prune-packed &&
git verify-pack ${pack}.pack &&
git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'corruption in delta base reference of first delta (OBJ_REF_DELTA)' \
'create_new_pack &&
git prune-packed &&
do_corrupt_object $blob_2 2 < zero &&
git cat-file blob $blob_1 > /dev/null &&
test_must_fail git cat-file blob $blob_2 > /dev/null &&
test_must_fail git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... but having a loose copy allows for full recovery' \
'mv ${pack}.idx tmp &&
git hash-object -t blob -w file_2 &&
mv tmp ${pack}.idx &&
git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... and then a repack "clears" the corruption' \
'do_repack &&
git prune-packed &&
git verify-pack ${pack}.pack &&
git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'corruption #0 in delta base reference of first delta (OBJ_OFS_DELTA)' \
'create_new_pack --delta-base-offset &&
git prune-packed &&
do_corrupt_object $blob_2 2 < zero &&
git cat-file blob $blob_1 > /dev/null &&
test_must_fail git cat-file blob $blob_2 > /dev/null &&
test_must_fail git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... but having a loose copy allows for full recovery' \
'mv ${pack}.idx tmp &&
git hash-object -t blob -w file_2 &&
mv tmp ${pack}.idx &&
git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... and then a repack "clears" the corruption' \
'do_repack --delta-base-offset &&
git prune-packed &&
git verify-pack ${pack}.pack &&
git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'corruption #1 in delta base reference of first delta (OBJ_OFS_DELTA)' \
'create_new_pack --delta-base-offset &&
git prune-packed &&
printf "\001" | do_corrupt_object $blob_2 2 &&
git cat-file blob $blob_1 > /dev/null &&
test_must_fail git cat-file blob $blob_2 > /dev/null &&
test_must_fail git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... but having a loose copy allows for full recovery' \
'mv ${pack}.idx tmp &&
git hash-object -t blob -w file_2 &&
mv tmp ${pack}.idx &&
git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... and then a repack "clears" the corruption' \
'do_repack --delta-base-offset &&
git prune-packed &&
git verify-pack ${pack}.pack &&
git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'... and a redundant pack allows for full recovery too' \
'do_corrupt_object $blob_2 2 < zero &&
git cat-file blob $blob_1 > /dev/null &&
test_must_fail git cat-file blob $blob_2 > /dev/null &&
test_must_fail git cat-file blob $blob_3 > /dev/null &&
mv ${pack}.idx tmp &&
git hash-object -t blob -w file_1 &&
git hash-object -t blob -w file_2 &&
printf "$blob_1\n$blob_2\n" | git pack-objects .git/objects/pack/pack &&
git prune-packed &&
mv tmp ${pack}.idx &&
git cat-file blob $blob_1 > /dev/null &&
git cat-file blob $blob_2 > /dev/null &&
git cat-file blob $blob_3 > /dev/null'
test_expect_success \
'corrupting header to have too small output buffer fails unpack' \
'create_new_pack &&
git prune-packed &&
printf "\262\001" | do_corrupt_object $blob_1 0 &&
test_must_fail git cat-file blob $blob_1 > /dev/null &&
test_must_fail git cat-file blob $blob_2 > /dev/null &&
test_must_fail git cat-file blob $blob_3 > /dev/null'
test_done