[PATCH 4/5] libarchive: integrate security fixes

[Ross Burton <ross.burton@intel.com>]

Fix the following CVEs by backporting patches from upstream:
- CVE-2019-1000019
- CVE-2019-1000020
- CVE-2018-1000877
- CVE-2018-1000878
- CVE-2018-1000879
- CVE-2018-1000880

Signed-off-by: Ross Burton <ross.burton@intel.com>
---
 .../libarchive/libarchive/CVE-2018-1000877.patch   | 38 +++++++++++
 .../libarchive/libarchive/CVE-2018-1000878.patch   | 79 ++++++++++++++++++++++
 .../libarchive/libarchive/CVE-2018-1000879.patch   | 50 ++++++++++++++
 .../libarchive/libarchive/CVE-2018-1000880.patch   | 44 ++++++++++++
 .../libarchive/libarchive/CVE-2019-1000019.patch   | 59 ++++++++++++++++
 .../libarchive/libarchive/CVE-2019-1000020.patch   | 61 +++++++++++++++++
 .../libarchive/libarchive_3.3.3.bb                 |  6 ++
 7 files changed, 337 insertions(+)
 create mode 100644 meta/recipes-extended/libarchive/libarchive/CVE-2018-1000877.patch
 create mode 100644 meta/recipes-extended/libarchive/libarchive/CVE-2018-1000878.patch
 create mode 100644 meta/recipes-extended/libarchive/libarchive/CVE-2018-1000879.patch
 create mode 100644 meta/recipes-extended/libarchive/libarchive/CVE-2018-1000880.patch
 create mode 100644 meta/recipes-extended/libarchive/libarchive/CVE-2019-1000019.patch
 create mode 100644 meta/recipes-extended/libarchive/libarchive/CVE-2019-1000020.patch

diff --git a/meta/recipes-extended/libarchive/libarchive/CVE-2018-1000877.patch b/meta/recipes-extended/libarchive/libarchive/CVE-2018-1000877.patch
new file mode 100644
index 00000000000..ce638370bd4
--- /dev/null
+++ b/meta/recipes-extended/libarchive/libarchive/CVE-2018-1000877.patch
@@ -0,0 +1,38 @@
+CVE: CVE-2018-1000877
+Upstream-Status: Backport
+Signed-off-by: Ross Burton <ross.burton@intel.com>
+
+From 021efa522ad729ff0f5806c4ce53e4a6cc1daa31 Mon Sep 17 00:00:00 2001
+From: Daniel Axtens <dja@axtens.net>
+Date: Tue, 20 Nov 2018 17:56:29 +1100
+Subject: [PATCH] Avoid a double-free when a window size of 0 is specified
+
+new_size can be 0 with a malicious or corrupted RAR archive.
+
+realloc(area, 0) is equivalent to free(area), so the region would
+be free()d here and the free()d again in the cleanup function.
+
+Found with a setup running AFL, afl-rb, and qsym.
+---
+ libarchive/archive_read_support_format_rar.c | 5 +++++
+ 1 file changed, 5 insertions(+)
+
+diff --git a/libarchive/archive_read_support_format_rar.c b/libarchive/archive_read_support_format_rar.c
+index 23452222..6f419c27 100644
+--- a/libarchive/archive_read_support_format_rar.c
++++ b/libarchive/archive_read_support_format_rar.c
+@@ -2300,6 +2300,11 @@ parse_codes(struct archive_read *a)
+       new_size = DICTIONARY_MAX_SIZE;
+     else
+       new_size = rar_fls((unsigned int)rar->unp_size) << 1;
++    if (new_size == 0) {
++      archive_set_error(&a->archive, ARCHIVE_ERRNO_FILE_FORMAT,
++                        "Zero window size is invalid.");
++      return (ARCHIVE_FATAL);
++    }
+     new_window = realloc(rar->lzss.window, new_size);
+     if (new_window == NULL) {
+       archive_set_error(&a->archive, ENOMEM,
+-- 
+2.20.0
+
diff --git a/meta/recipes-extended/libarchive/libarchive/CVE-2018-1000878.patch b/meta/recipes-extended/libarchive/libarchive/CVE-2018-1000878.patch
new file mode 100644
index 00000000000..7468fd3c935
--- /dev/null
+++ b/meta/recipes-extended/libarchive/libarchive/CVE-2018-1000878.patch
@@ -0,0 +1,79 @@
+CVE: CVE-2018-1000878
+Upstream-Status: Backport
+Signed-off-by: Ross Burton <ross.burton@intel.com>
+
+From bfcfe6f04ed20db2504db8a254d1f40a1d84eb28 Mon Sep 17 00:00:00 2001
+From: Daniel Axtens <dja@axtens.net>
+Date: Tue, 4 Dec 2018 00:55:22 +1100
+Subject: [PATCH] rar: file split across multi-part archives must match
+
+Fuzzing uncovered some UAF and memory overrun bugs where a file in a
+single file archive reported that it was split across multiple
+volumes. This was caused by ppmd7 operations calling
+rar_br_fillup. This would invoke rar_read_ahead, which would in some
+situations invoke archive_read_format_rar_read_header.  That would
+check the new file name against the old file name, and if they didn't
+match up it would free the ppmd7 buffer and allocate a new
+one. However, because the ppmd7 decoder wasn't actually done with the
+buffer, it would continue to used the freed buffer. Both reads and
+writes to the freed region can be observed.
+
+This is quite tricky to solve: once the buffer has been freed it is
+too late, as the ppmd7 decoder functions almost universally assume
+success - there's no way for ppmd_read to signal error, nor are there
+good ways for functions like Range_Normalise to propagate them. So we
+can't detect after the fact that we're in an invalid state - e.g. by
+checking rar->cursor, we have to prevent ourselves from ever ending up
+there. So, when we are in the dangerous part or rar_read_ahead that
+assumes a valid split, we set a flag force read_header to either go
+down the path for split files or bail. This means that the ppmd7
+decoder keeps a valid buffer and just runs out of data.
+
+Found with a combination of AFL, afl-rb and qsym.
+---
+ libarchive/archive_read_support_format_rar.c | 9 +++++++++
+ 1 file changed, 9 insertions(+)
+
+diff --git a/libarchive/archive_read_support_format_rar.c b/libarchive/archive_read_support_format_rar.c
+index 6f419c27..a8cc5c94 100644
+--- a/libarchive/archive_read_support_format_rar.c
++++ b/libarchive/archive_read_support_format_rar.c
+@@ -258,6 +258,7 @@ struct rar
+   struct data_block_offsets *dbo;
+   unsigned int cursor;
+   unsigned int nodes;
++  char filename_must_match;
+ 
+   /* LZSS members */
+   struct huffman_code maincode;
+@@ -1560,6 +1561,12 @@ read_header(struct archive_read *a, struct archive_entry *entry,
+     }
+     return ret;
+   }
++  else if (rar->filename_must_match)
++  {
++    archive_set_error(&a->archive, ARCHIVE_ERRNO_FILE_FORMAT,
++      "Mismatch of file parts split across multi-volume archive");
++    return (ARCHIVE_FATAL);
++  }
+ 
+   rar->filename_save = (char*)realloc(rar->filename_save,
+                                       filename_size + 1);
+@@ -2933,12 +2940,14 @@ rar_read_ahead(struct archive_read *a, size_t min, ssize_t *avail)
+     else if (*avail == 0 && rar->main_flags & MHD_VOLUME &&
+       rar->file_flags & FHD_SPLIT_AFTER)
+     {
++      rar->filename_must_match = 1;
+       ret = archive_read_format_rar_read_header(a, a->entry);
+       if (ret == (ARCHIVE_EOF))
+       {
+         rar->has_endarc_header = 1;
+         ret = archive_read_format_rar_read_header(a, a->entry);
+       }
++      rar->filename_must_match = 0;
+       if (ret != (ARCHIVE_OK))
+         return NULL;
+       return rar_read_ahead(a, min, avail);
+-- 
+2.20.0
+
diff --git a/meta/recipes-extended/libarchive/libarchive/CVE-2018-1000879.patch b/meta/recipes-extended/libarchive/libarchive/CVE-2018-1000879.patch
new file mode 100644
index 00000000000..9f25932a1ab
--- /dev/null
+++ b/meta/recipes-extended/libarchive/libarchive/CVE-2018-1000879.patch
@@ -0,0 +1,50 @@
+CVE: CVE-2018-1000879
+Upstream-Status: Backport
+Signed-off-by: Ross Burton <ross.burton@intel.com>
+
+From 15bf44fd2c1ad0e3fd87048b3fcc90c4dcff1175 Mon Sep 17 00:00:00 2001
+From: Daniel Axtens <dja@axtens.net>
+Date: Tue, 4 Dec 2018 14:29:42 +1100
+Subject: [PATCH] Skip 0-length ACL fields
+
+Currently, it is possible to create an archive that crashes bsdtar
+with a malformed ACL:
+
+Program received signal SIGSEGV, Segmentation fault.
+archive_acl_from_text_l (acl=<optimised out>, text=0x7e2e92 "", want_type=<optimised out>, sc=<optimised out>) at libarchive/archive_acl.c:1726
+1726				switch (*s) {
+(gdb) p n
+$1 = 1
+(gdb) p field[n]
+$2 = {start = 0x0, end = 0x0}
+
+Stop this by checking that the length is not zero before beginning
+the switch statement.
+
+I am pretty sure this is the bug mentioned in the qsym paper [1],
+and I was able to replicate it with a qsym + AFL + afl-rb setup.
+
+[1] https://www.usenix.org/conference/usenixsecurity18/presentation/yun
+---
+ libarchive/archive_acl.c | 5 +++++
+ 1 file changed, 5 insertions(+)
+
+diff --git a/libarchive/archive_acl.c b/libarchive/archive_acl.c
+index 512beee1..7beeee86 100644
+--- a/libarchive/archive_acl.c
++++ b/libarchive/archive_acl.c
+@@ -1723,6 +1723,11 @@ archive_acl_from_text_l(struct archive_acl *acl, const char *text,
+ 			st = field[n].start + 1;
+ 			len = field[n].end - field[n].start;
+ 
++			if (len == 0) {
++				ret = ARCHIVE_WARN;
++				continue;
++			}
++
+ 			switch (*s) {
+ 			case 'u':
+ 				if (len == 1 || (len == 4
+-- 
+2.20.0
+
diff --git a/meta/recipes-extended/libarchive/libarchive/CVE-2018-1000880.patch b/meta/recipes-extended/libarchive/libarchive/CVE-2018-1000880.patch
new file mode 100644
index 00000000000..bc264a12423
--- /dev/null
+++ b/meta/recipes-extended/libarchive/libarchive/CVE-2018-1000880.patch
@@ -0,0 +1,44 @@
+CVE: CVE-2018-1000880
+Upstream-Status: Backport
+Signed-off-by: Ross Burton <ross.burton@intel.com>
+
+From 9c84b7426660c09c18cc349f6d70b5f8168b5680 Mon Sep 17 00:00:00 2001
+From: Daniel Axtens <dja@axtens.net>
+Date: Tue, 4 Dec 2018 16:33:42 +1100
+Subject: [PATCH] warc: consume data once read
+
+The warc decoder only used read ahead, it wouldn't actually consume
+data that had previously been printed. This means that if you specify
+an invalid content length, it will just reprint the same data over
+and over and over again until it hits the desired length.
+
+This means that a WARC resource with e.g.
+Content-Length: 666666666666666666666666666666666666666666666666666666666666666666666666666666666666666666666666666666666666665
+but only a few hundred bytes of data, causes a quasi-infinite loop.
+
+Consume data in subsequent calls to _warc_read.
+
+Found with an AFL + afl-rb + qsym setup.
+---
+ libarchive/archive_read_support_format_warc.c | 5 +++++
+ 1 file changed, 5 insertions(+)
+
+diff --git a/libarchive/archive_read_support_format_warc.c b/libarchive/archive_read_support_format_warc.c
+index e8753853..e8fc8428 100644
+--- a/libarchive/archive_read_support_format_warc.c
++++ b/libarchive/archive_read_support_format_warc.c
+@@ -386,6 +386,11 @@ _warc_read(struct archive_read *a, const void **buf, size_t *bsz, int64_t *off)
+ 		return (ARCHIVE_EOF);
+ 	}
+ 
++	if (w->unconsumed) {
++		__archive_read_consume(a, w->unconsumed);
++		w->unconsumed = 0U;
++	}
++
+ 	rab = __archive_read_ahead(a, 1U, &nrd);
+ 	if (nrd < 0) {
+ 		*bsz = 0U;
+-- 
+2.20.0
+
diff --git a/meta/recipes-extended/libarchive/libarchive/CVE-2019-1000019.patch b/meta/recipes-extended/libarchive/libarchive/CVE-2019-1000019.patch
new file mode 100644
index 00000000000..f6f1add5e06
--- /dev/null
+++ b/meta/recipes-extended/libarchive/libarchive/CVE-2019-1000019.patch
@@ -0,0 +1,59 @@
+CVE: CVE-2018-1000019
+Upstream-Status: Backport
+Signed-off-by: Ross Burton <ross.burton@intel.com>
+
+From 65a23f5dbee4497064e9bb467f81138a62b0dae1 Mon Sep 17 00:00:00 2001
+From: Daniel Axtens <dja@axtens.net>
+Date: Tue, 1 Jan 2019 16:01:40 +1100
+Subject: [PATCH 2/2] 7zip: fix crash when parsing certain archives
+
+Fuzzing with CRCs disabled revealed that a call to get_uncompressed_data()
+would sometimes fail to return at least 'minimum' bytes. This can cause
+the crc32() invocation in header_bytes to read off into invalid memory.
+
+A specially crafted archive can use this to cause a crash.
+
+An ASAN trace is below, but ASAN is not required - an uninstrumented
+binary will also crash.
+
+==7719==ERROR: AddressSanitizer: SEGV on unknown address 0x631000040000 (pc 0x7fbdb3b3ec1d bp 0x7ffe77a51310 sp 0x7ffe77a51150 T0)
+==7719==The signal is caused by a READ memory access.
+    #0 0x7fbdb3b3ec1c in crc32_z (/lib/x86_64-linux-gnu/libz.so.1+0x2c1c)
+    #1 0x84f5eb in header_bytes (/tmp/libarchive/bsdtar+0x84f5eb)
+    #2 0x856156 in read_Header (/tmp/libarchive/bsdtar+0x856156)
+    #3 0x84e134 in slurp_central_directory (/tmp/libarchive/bsdtar+0x84e134)
+    #4 0x849690 in archive_read_format_7zip_read_header (/tmp/libarchive/bsdtar+0x849690)
+    #5 0x5713b7 in _archive_read_next_header2 (/tmp/libarchive/bsdtar+0x5713b7)
+    #6 0x570e63 in _archive_read_next_header (/tmp/libarchive/bsdtar+0x570e63)
+    #7 0x6f08bd in archive_read_next_header (/tmp/libarchive/bsdtar+0x6f08bd)
+    #8 0x52373f in read_archive (/tmp/libarchive/bsdtar+0x52373f)
+    #9 0x5257be in tar_mode_x (/tmp/libarchive/bsdtar+0x5257be)
+    #10 0x51daeb in main (/tmp/libarchive/bsdtar+0x51daeb)
+    #11 0x7fbdb27cab96 in __libc_start_main /build/glibc-OTsEL5/glibc-2.27/csu/../csu/libc-start.c:310
+    #12 0x41dd09 in _start (/tmp/libarchive/bsdtar+0x41dd09)
+
+This was primarly done with afl and FairFuzz. Some early corpus entries
+may have been generated by qsym.
+---
+ libarchive/archive_read_support_format_7zip.c | 8 +-------
+ 1 file changed, 1 insertion(+), 7 deletions(-)
+
+diff --git a/libarchive/archive_read_support_format_7zip.c b/libarchive/archive_read_support_format_7zip.c
+index bccbf8966..b6d1505d3 100644
+--- a/libarchive/archive_read_support_format_7zip.c
++++ b/libarchive/archive_read_support_format_7zip.c
+@@ -2964,13 +2964,7 @@ get_uncompressed_data(struct archive_read *a, const void **buff, size_t size,
+ 	if (zip->codec == _7Z_COPY && zip->codec2 == (unsigned long)-1) {
+ 		/* Copy mode. */
+ 
+-		/*
+-		 * Note: '1' here is a performance optimization.
+-		 * Recall that the decompression layer returns a count of
+-		 * available bytes; asking for more than that forces the
+-		 * decompressor to combine reads by copying data.
+-		 */
+-		*buff = __archive_read_ahead(a, 1, &bytes_avail);
++		*buff = __archive_read_ahead(a, minimum, &bytes_avail);
+ 		if (bytes_avail <= 0) {
+ 			archive_set_error(&a->archive,
+ 			    ARCHIVE_ERRNO_FILE_FORMAT,
diff --git a/meta/recipes-extended/libarchive/libarchive/CVE-2019-1000020.patch b/meta/recipes-extended/libarchive/libarchive/CVE-2019-1000020.patch
new file mode 100644
index 00000000000..3e639213464
--- /dev/null
+++ b/meta/recipes-extended/libarchive/libarchive/CVE-2019-1000020.patch
@@ -0,0 +1,61 @@
+CVE: CVE-2018-1000020
+Upstream-Status: Backport
+Signed-off-by: Ross Burton <ross.burton@intel.com>
+
+From 8312eaa576014cd9b965012af51bc1f967b12423 Mon Sep 17 00:00:00 2001
+From: Daniel Axtens <dja@axtens.net>
+Date: Tue, 1 Jan 2019 17:10:49 +1100
+Subject: [PATCH 1/2] iso9660: Fail when expected Rockridge extensions is
+ missing
+
+A corrupted or malicious ISO9660 image can cause read_CE() to loop
+forever.
+
+read_CE() calls parse_rockridge(), expecting a Rockridge extension
+to be read. However, parse_rockridge() is structured as a while
+loop starting with a sanity check, and if the sanity check fails
+before the loop has run, the function returns ARCHIVE_OK without
+advancing the position in the file. This causes read_CE() to retry
+indefinitely.
+
+Make parse_rockridge() return ARCHIVE_WARN if it didn't read an
+extension. As someone with no real knowledge of the format, this
+seems more apt than ARCHIVE_FATAL, but both the call-sites escalate
+it to a fatal error immediately anyway.
+
+Found with a combination of AFL, afl-rb (FairFuzz) and qsym.
+---
+ libarchive/archive_read_support_format_iso9660.c | 11 ++++++++++-
+ 1 file changed, 10 insertions(+), 1 deletion(-)
+
+diff --git a/libarchive/archive_read_support_format_iso9660.c b/libarchive/archive_read_support_format_iso9660.c
+index 28acfefbb..bad8f1dfe 100644
+--- a/libarchive/archive_read_support_format_iso9660.c
++++ b/libarchive/archive_read_support_format_iso9660.c
+@@ -2102,6 +2102,7 @@ parse_rockridge(struct archive_read *a, struct file_info *file,
+     const unsigned char *p, const unsigned char *end)
+ {
+ 	struct iso9660 *iso9660;
++	int entry_seen = 0;
+ 
+ 	iso9660 = (struct iso9660 *)(a->format->data);
+ 
+@@ -2257,8 +2258,16 @@ parse_rockridge(struct archive_read *a, struct file_info *file,
+ 		}
+ 
+ 		p += p[2];
++		entry_seen = 1;
++	}
++
++	if (entry_seen)
++		return (ARCHIVE_OK);
++	else {
++		archive_set_error(&a->archive, ARCHIVE_ERRNO_FILE_FORMAT,
++				  "Tried to parse Rockridge extensions, but none found");
++		return (ARCHIVE_WARN);
+ 	}
+-	return (ARCHIVE_OK);
+ }
+ 
+ static int
+
diff --git a/meta/recipes-extended/libarchive/libarchive_3.3.3.bb b/meta/recipes-extended/libarchive/libarchive_3.3.3.bb
index 46a3d437626..af5ca65297b 100644
--- a/meta/recipes-extended/libarchive/libarchive_3.3.3.bb
+++ b/meta/recipes-extended/libarchive/libarchive_3.3.3.bb
@@ -34,6 +34,12 @@ EXTRA_OECONF += "--enable-largefile"
 SRC_URI = "http://libarchive.org/downloads/libarchive-${PV}.tar.gz \
            file://non-recursive-extract-and-list.patch \
            file://bug1066.patch \
+           file://CVE-2018-1000877.patch \
+           file://CVE-2018-1000878.patch \
+           file://CVE-2018-1000879.patch \
+           file://CVE-2018-1000880.patch \
+           file://CVE-2019-1000019.patch \
+           file://CVE-2019-1000020.patch \
 "
 
 SRC_URI[md5sum] = "4038e366ca5b659dae3efcc744e72120"
-- 
2.11.0