Accept as many selectors as the file format allows (fixes CVE-2019-12900 regression)

SOURCES/0001-Accept-as-many-selectors-as-the-file-format-allows.patch

@@ -0,0 +1,81 @@
+From b07b105d1b66e32760095e3602261738443b9e13 Mon Sep 17 00:00:00 2001
+From: Mark Wielaard <mark@klomp.org>
+Date: Wed, 3 Jul 2019 01:28:11 +0200
+Subject: [PATCH] Accept as many selectors as the file format allows.
+
+But ignore any larger than the theoretical maximum, BZ_MAX_SELECTORS.
+
+The theoretical maximum number of selectors depends on the maximum
+blocksize (900000 bytes) and the number of symbols (50) that can be
+encoded with a different Huffman tree. BZ_MAX_SELECTORS is 18002.
+
+But the bzip2 file format allows the number of selectors to be encoded
+with 15 bits (because 18002 isn't a factor of 2 and doesn't fit in
+14 bits). So the file format maximum is 32767 selectors.
+
+Some bzip2 encoders might actually have written out more selectors
+than the theoretical maximum because they rounded up the number of
+selectors to some convenient factor of 8.
+
+The extra 14766 selectors can never be validly used by the decompression
+algorithm. So we can read them, but then discard them.
+
+This is effectively what was done (by accident) before we added a
+check for nSelectors to be at most BZ_MAX_SELECTORS to mitigate
+CVE-2019-12900.
+
+The extra selectors were written out after the array inside the
+EState struct. But the struct has extra space allocated after the
+selector arrays of 18060 bytes (which is larger than 14766).
+All of which will be initialized later (so the overwrite of that
+space with extra selector values would have been harmless).
+---
+ compress.c   |  2 +-
+ decompress.c | 10 ++++++++--
+ 2 files changed, 9 insertions(+), 3 deletions(-)
+
+diff --git a/compress.c b/compress.c
+index 237620d..76adee6 100644
+--- a/compress.c
++++ b/compress.c
+@@ -454,7 +454,7 @@ void sendMTFValues ( EState* s )
+ 
+    AssertH( nGroups < 8, 3002 );
+    AssertH( nSelectors < 32768 &&
+-            nSelectors <= (2 + (900000 / BZ_G_SIZE)),
++            nSelectors <= BZ_MAX_SELECTORS,
+             3003 );
+ 
+ 
+diff --git a/decompress.c b/decompress.c
+index 20ce493..3303499 100644
+--- a/decompress.c
++++ b/decompress.c
+@@ -287,7 +287,7 @@ Int32 BZ2_decompress ( DState* s )
+       GET_BITS(BZ_X_SELECTOR_1, nGroups, 3);
+       if (nGroups < 2 || nGroups > BZ_N_GROUPS) RETURN(BZ_DATA_ERROR);
+       GET_BITS(BZ_X_SELECTOR_2, nSelectors, 15);
+-      if (nSelectors < 1 || nSelectors > BZ_MAX_SELECTORS) RETURN(BZ_DATA_ERROR);
++      if (nSelectors < 1) RETURN(BZ_DATA_ERROR);
+       for (i = 0; i < nSelectors; i++) {
+          j = 0;
+          while (True) {
+@@ -296,8 +296,14 @@ Int32 BZ2_decompress ( DState* s )
+             j++;
+             if (j >= nGroups) RETURN(BZ_DATA_ERROR);
+          }
+-         s->selectorMtf[i] = j;
++         /* Having more than BZ_MAX_SELECTORS doesn't make much sense
++            since they will never be used, but some implementations might
++            "round up" the number of selectors, so just ignore those. */
++         if (i < BZ_MAX_SELECTORS)
++           s->selectorMtf[i] = j;
+       }
++      if (nSelectors > BZ_MAX_SELECTORS)
++        nSelectors = BZ_MAX_SELECTORS;
+ 
+       /*--- Undo the MTF values for the selectors. ---*/
+       {
+-- 
+2.43.5
+

SPECS/bzip2.spec

@@ -3,7 +3,7 @@
 Summary: A file compression utility
 Name: bzip2
 Version: 1.0.6
-Release: 27%{?dist}
+Release: 27%{?dist}.alma.1
 License: BSD
 Group: Applications/File
 URL: http://www.bzip.org/
@@ -19,6 +19,10 @@ Patch3: bzip2-ldflags.patch
 Patch4: set-out-file-to-null.patch
 Patch5: decompress-out-of-bounds.patch
 
+# AlmaLinux patches
+# https://inbox.sourceware.org/bzip2-devel/20241108214034.GC8315@gnu.wildebeest.org/
+Patch100: 0001-Accept-as-many-selectors-as-the-file-format-allows.patch
+
 %description
 Bzip2 is a freely available, patent-free, high quality data compressor.
 Bzip2 compresses files to within 10 to 15 percent of the capabilities
@@ -65,6 +69,8 @@ Static libraries for applications using the bzip2 compression format.
 %patch4 -p1 -b .bzip2recover
 %patch5 -p1
 
+%patch100 -p1
+
 cp -a %{SOURCE1} .
 sed -i "s|^libdir=|libdir=%{_libdir}|" bzip2.pc
 
@@ -142,6 +148,9 @@ ln -s bzgrep.1 $RPM_BUILD_ROOT%{_mandir}/man1/bzfgrep.1
 %{_libdir}/pkgconfig/bzip2.pc
 
 %changelog
+* Fri Nov 15 2024 Andrew Lukoshko <alukoshko@almalinux.org> - 1.0.6-27.alma.1
+- Accept as many selectors as the file format allows (fixes CVE-2019-12900 regression)
+
 * Tue Oct 29 2024 Jacek Migacz <jmigacz@redhat.com> - 1.0.6-27
 - Fixes out of bounds access in BZ2_decompress (RHEL-64929)