Hello Emil and all, Thanks for the clear and easily reproducible bug report.
Attached a suggested fix. Comments very welcomed, - Assaf
>From 11330058443e7cc92b4a53322d810725d42b4e34 Mon Sep 17 00:00:00 2001 From: Assaf Gordon <assafgor...@gmail.com> Date: Mon, 16 Aug 2021 15:03:36 -0600 Subject: [PATCH] basenc: fix bug49741: using wrong decoding buffer length Emil Lundberg <lundberg.e...@gmail.com> reports in https://bugs.gnu.org/49741 about a 'basenc --base64 -d' decoding bug. The input buffer was not divisible by 3, resulting in decoding errors. * NEWS: Mention fix. * src/basenc.c (DEC_BLOCKSIZE): Change from 1024*5 to 4200 (35*3*5*8) which is divisible by 3,4,5,8 - satisfying both base32 and base64; Use compile-time verify() macro to enforce the above. * tests/misc/basenc.pl: Add test. --- NEWS | 4 ++++ src/basenc.c | 4 +++- tests/misc/basenc.pl | 9 +++++++++ 3 files changed, 16 insertions(+), 1 deletion(-) diff --git a/NEWS b/NEWS index ddec56bdf..d490ed101 100644 --- a/NEWS +++ b/NEWS @@ -60,6 +60,10 @@ GNU coreutils NEWS -*- outline -*- invalid combinations of case character classes. [bug introduced in coreutils-8.6] + basenc --base64 --decode no longer silently discard decoded characters + on (1024*5) buffer boundaries + [bug introduced in coreutils-8.31] + ** Changes in behavior cp and install now default to copy-on-write (COW) if available. diff --git a/src/basenc.c b/src/basenc.c index 5c97a3652..2ffdb2d27 100644 --- a/src/basenc.c +++ b/src/basenc.c @@ -213,7 +213,9 @@ verify (DEC_BLOCKSIZE % 12 == 0); /* So complete encoded blocks are used. */ /* Note that increasing this may decrease performance if --ignore-garbage is used, because of the memmove operation below. */ -# define DEC_BLOCKSIZE (1024*5) +# define DEC_BLOCKSIZE (4200) +verify (DEC_BLOCKSIZE % 40 == 0); /* complete encoded blocks for base32 */ +verify (DEC_BLOCKSIZE % 12 == 0); /* complete encoded blocks for base64 */ static int (*base_length) (int i); static bool (*isbase) (char ch); diff --git a/tests/misc/basenc.pl b/tests/misc/basenc.pl index 3383aaeef..ac5394731 100755 --- a/tests/misc/basenc.pl +++ b/tests/misc/basenc.pl @@ -37,6 +37,13 @@ my $base64url_out_nl = $base64url_out; $base64url_out_nl =~ s/(..)/\1\n/g; # add newline every two characters +# Bug 49741: +# The input is 'abc' in base64, in an 8K buffer (larger than 1024*5, +# the buffer size which caused the bug). +my $base64_bug49741_in = "YWJj" x 2000 ; +my $base64_bug49741_out = "abc" x 2000 ; + + my $base32_in = "\xfd\xd8\x07\xd1\xa5"; my $base32_out = "7XMAPUNF"; my $x = $base32_out; @@ -111,6 +118,8 @@ my @Tests = ['b64u_7', '--base64url -d', {IN=>$base64_out}, {EXIT=>1}, {ERR=>"$prog: invalid input\n"}], + ['b64_bug49741', '--base64 -d', {IN=>$base64_bug49741_in}, + {OUT=>$base64_bug49741_out}], -- 2.20.1
