libarchive: do not extract unsafe symlinks unless $EXTRACT_UNSAFE_SYMLINKS=1

function                                             old     new   delta
unsafe_symlink_target                                  -     147    +147
unzip_main                                          2711    2732     +21
copy_file                                           1657    1678     +21
tar_main                                             999     971     -28
data_extract_all                                    1038     984     -54
------------------------------------------------------------------------------
(add/remove: 2/0 grow/shrink: 2/2 up/down: 189/-82)           Total: 107 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>

3 files changed, 65 insertions, 22 deletions

diff --git a/archival/libarchive/Kbuild.src b/archival/libarchive/Kbuild.src
index 942e755b9..e1a8a7529 100644
--- a/archival/libarchive/Kbuild.src
+++ b/archival/libarchive/Kbuild.src
@@ -12,6 +12,8 @@ COMMON_FILES:= \
 	data_extract_all.o \
 	data_extract_to_stdout.o \
 \
+	unsafe_symlink_target.o \
+\
 	filter_accept_all.o \
 	filter_accept_list.o \
 	filter_accept_reject_list.o \
diff --git a/archival/libarchive/data_extract_all.c b/archival/libarchive/data_extract_all.c
index 1ce927c2f..e658444e0 100644
--- a/archival/libarchive/data_extract_all.c
+++ b/archival/libarchive/data_extract_all.c
@@ -129,9 +129,7 @@ void FAST_FUNC data_extract_all(archive_handle_t *archive_handle)
 		if (res != 0 && !(archive_handle->ah_flags & ARCHIVE_EXTRACT_QUIET)) {
 			/* shared message */
 			bb_perror_msg("can't create %slink '%s' to '%s'",
-					"hard",
-					dst_name,
-					hard_link
+				"hard",	dst_name, hard_link
 			);
 		}
 		/* Hardlinks have no separate mode/ownership, skip chown/chmod */
@@ -181,7 +179,9 @@ void FAST_FUNC data_extract_all(archive_handle_t *archive_handle)
 //TODO: what if file_header->link_target == NULL (say, corrupted tarball?)
 
 		/* To avoid a directory traversal attack via symlinks,
-		 * for certain link targets postpone creation of symlinks.
+		 * do not restore symlinks with ".." components
+		 * or symlinks starting with "/", unless a magic
+		 * envvar is set.
 		 *
 		 * For example, consider a .tar created via:
 		 *  $ tar cvf bug.tar anything.txt
@@ -199,24 +199,17 @@ void FAST_FUNC data_extract_all(archive_handle_t *archive_handle)
 		 *
 		 * Untarring bug.tar would otherwise place evil.py in '/tmp'.
 		 */
-		if (file_header->link_target[0] == '/'
-		 || strstr(file_header->link_target, "..")
-		) {
-			llist_add_to(&archive_handle->symlink_placeholders,
-				xasprintf("%s%c%s", file_header->name, '\0', file_header->link_target)
-			);
-			break;
-		}
-		res = symlink(file_header->link_target, dst_name);
-		if (res != 0
-		 && !(archive_handle->ah_flags & ARCHIVE_EXTRACT_QUIET)
-		) {
-			/* shared message */
-			bb_perror_msg("can't create %slink '%s' to '%s'",
-				"sym",
-				dst_name,
-				file_header->link_target
-			);
+		if (!unsafe_symlink_target(file_header->link_target)) {
+			res = symlink(file_header->link_target, dst_name);
+			if (res != 0
+			 && !(archive_handle->ah_flags & ARCHIVE_EXTRACT_QUIET)
+			) {
+				/* shared message */
+				bb_perror_msg("can't create %slink '%s' to '%s'",
+					"sym",
+					dst_name, file_header->link_target
+				);
+			}
 		}
 		break;
 	case S_IFSOCK:
diff --git a/archival/libarchive/unsafe_symlink_target.c b/archival/libarchive/unsafe_symlink_target.c
new file mode 100644
index 000000000..441ba8b24
--- /dev/null
+++ b/archival/libarchive/unsafe_symlink_target.c
@@ -0,0 +1,48 @@
+/* vi: set sw=4 ts=4: */
+/*
+ * Licensed under GPLv2 or later, see file LICENSE in this source tree.
+ */
+#include "libbb.h"
+#include "bb_archive.h"
+
+int FAST_FUNC unsafe_symlink_target(const char *target)
+{
+	const char *dot;
+
+	if (target[0] == '/') {
+		const char *var;
+ unsafe:
+		var = getenv("EXTRACT_UNSAFE_SYMLINKS");
+		if (var) {
+			if (LONE_CHAR(var, '1'))
+				return 0; /* pretend it's safe */
+			return 1; /* "UNSAFE!" */
+		}
+		bb_error_msg("skipping unsafe symlink to '%s' in archive,"
+			" set %s=1 to extract",
+			target,
+			"EXTRACT_UNSAFE_SYMLINKS"
+		);
+		/* Prevent further messages */
+		setenv("EXTRACT_UNSAFE_SYMLINKS", "0", 0);
+		return 1; /* "UNSAFE!" */
+	}
+
+	dot = target;
+	for (;;) {
+		dot = strchr(dot, '.');
+		if (!dot)
+			return 0; /* safe target */
+
+		/* Is it a path component starting with ".."? */
+		if ((dot[1] == '.')
+		 && (dot == target || dot[-1] == '/')
+		    /* Is it exactly ".."? */
+		 && (dot[2] == '/' || dot[2] == '\0')
+		) {
+			goto unsafe;
+		}
+		/* NB: it can even be trailing ".", should only add 1 */
+		dot += 1;
+	}
+}