aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--gnu/local.mk1
-rw-r--r--gnu/packages/patches/runc-CVE-2019-5736.patch343
-rw-r--r--gnu/packages/virtualization.scm6
3 files changed, 348 insertions, 2 deletions
diff --git a/gnu/local.mk b/gnu/local.mk
index 9fe34cb1dc..16bb704933 100644
--- a/gnu/local.mk
+++ b/gnu/local.mk
@@ -1207,6 +1207,7 @@ dist_patch_DATA = \
%D%/packages/patches/ruby-concurrent-test-arm.patch \
%D%/packages/patches/ruby-rack-ignore-failing-test.patch \
%D%/packages/patches/ruby-tzinfo-data-ignore-broken-test.patch\
+ %D%/packages/patches/runc-CVE-2019-5736.patch \
%D%/packages/patches/rust-1.19-mrustc.patch \
%D%/packages/patches/rust-1.25-accept-more-detailed-gdb-lines.patch \
%D%/packages/patches/rust-bootstrap-stage0-test.patch \
diff --git a/gnu/packages/patches/runc-CVE-2019-5736.patch b/gnu/packages/patches/runc-CVE-2019-5736.patch
new file mode 100644
index 0000000000..f629fcbfb4
--- /dev/null
+++ b/gnu/packages/patches/runc-CVE-2019-5736.patch
@@ -0,0 +1,343 @@
+Fix CVE-2019-5736:
+
+https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2019-5736
+https://seclists.org/oss-sec/2019/q1/119
+
+Patch copied from upstream source repository:
+
+https://github.com/opencontainers/runc/commit/0a8e4117e7f715d5fbeef398405813ce8e88558b
+
+From 0a8e4117e7f715d5fbeef398405813ce8e88558b Mon Sep 17 00:00:00 2001
+From: Aleksa Sarai <asarai@suse.de>
+Date: Wed, 9 Jan 2019 13:40:01 +1100
+Subject: [PATCH] nsenter: clone /proc/self/exe to avoid exposing host binary
+ to container
+
+There are quite a few circumstances where /proc/self/exe pointing to a
+pretty important container binary is a _bad_ thing, so to avoid this we
+have to make a copy (preferably doing self-clean-up and not being
+writeable).
+
+We require memfd_create(2) -- though there is an O_TMPFILE fallback --
+but we can always extend this to use a scratch MNT_DETACH overlayfs or
+tmpfs. The main downside to this approach is no page-cache sharing for
+the runc binary (which overlayfs would give us) but this is far less
+complicated.
+
+This is only done during nsenter so that it happens transparently to the
+Go code, and any libcontainer users benefit from it. This also makes
+ExtraFiles and --preserve-fds handling trivial (because we don't need to
+worry about it).
+
+Fixes: CVE-2019-5736
+Co-developed-by: Christian Brauner <christian.brauner@ubuntu.com>
+Signed-off-by: Aleksa Sarai <asarai@suse.de>
+---
+ libcontainer/nsenter/cloned_binary.c | 268 +++++++++++++++++++++++++++
+ libcontainer/nsenter/nsexec.c | 11 ++
+ 2 files changed, 279 insertions(+)
+ create mode 100644 libcontainer/nsenter/cloned_binary.c
+
+diff --git a/libcontainer/nsenter/cloned_binary.c b/libcontainer/nsenter/cloned_binary.c
+new file mode 100644
+index 000000000..c8a42c23f
+--- /dev/null
++++ b/libcontainer/nsenter/cloned_binary.c
+@@ -0,0 +1,268 @@
++/*
++ * Copyright (C) 2019 Aleksa Sarai <cyphar@cyphar.com>
++ * Copyright (C) 2019 SUSE LLC
++ *
++ * Licensed under the Apache License, Version 2.0 (the "License");
++ * you may not use this file except in compliance with the License.
++ * You may obtain a copy of the License at
++ *
++ * http://www.apache.org/licenses/LICENSE-2.0
++ *
++ * Unless required by applicable law or agreed to in writing, software
++ * distributed under the License is distributed on an "AS IS" BASIS,
++ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
++ * See the License for the specific language governing permissions and
++ * limitations under the License.
++ */
++
++#define _GNU_SOURCE
++#include <unistd.h>
++#include <stdio.h>
++#include <stdlib.h>
++#include <stdbool.h>
++#include <string.h>
++#include <limits.h>
++#include <fcntl.h>
++#include <errno.h>
++
++#include <sys/types.h>
++#include <sys/stat.h>
++#include <sys/vfs.h>
++#include <sys/mman.h>
++#include <sys/sendfile.h>
++#include <sys/syscall.h>
++
++/* Use our own wrapper for memfd_create. */
++#if !defined(SYS_memfd_create) && defined(__NR_memfd_create)
++# define SYS_memfd_create __NR_memfd_create
++#endif
++#ifdef SYS_memfd_create
++# define HAVE_MEMFD_CREATE
++/* memfd_create(2) flags -- copied from <linux/memfd.h>. */
++# ifndef MFD_CLOEXEC
++# define MFD_CLOEXEC 0x0001U
++# define MFD_ALLOW_SEALING 0x0002U
++# endif
++int memfd_create(const char *name, unsigned int flags)
++{
++ return syscall(SYS_memfd_create, name, flags);
++}
++#endif
++
++/* This comes directly from <linux/fcntl.h>. */
++#ifndef F_LINUX_SPECIFIC_BASE
++# define F_LINUX_SPECIFIC_BASE 1024
++#endif
++#ifndef F_ADD_SEALS
++# define F_ADD_SEALS (F_LINUX_SPECIFIC_BASE + 9)
++# define F_GET_SEALS (F_LINUX_SPECIFIC_BASE + 10)
++#endif
++#ifndef F_SEAL_SEAL
++# define F_SEAL_SEAL 0x0001 /* prevent further seals from being set */
++# define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */
++# define F_SEAL_GROW 0x0004 /* prevent file from growing */
++# define F_SEAL_WRITE 0x0008 /* prevent writes */
++#endif
++
++#define RUNC_SENDFILE_MAX 0x7FFFF000 /* sendfile(2) is limited to 2GB. */
++#ifdef HAVE_MEMFD_CREATE
++# define RUNC_MEMFD_COMMENT "runc_cloned:/proc/self/exe"
++# define RUNC_MEMFD_SEALS \
++ (F_SEAL_SEAL | F_SEAL_SHRINK | F_SEAL_GROW | F_SEAL_WRITE)
++#endif
++
++static void *must_realloc(void *ptr, size_t size)
++{
++ void *old = ptr;
++ do {
++ ptr = realloc(old, size);
++ } while(!ptr);
++ return ptr;
++}
++
++/*
++ * Verify whether we are currently in a self-cloned program (namely, is
++ * /proc/self/exe a memfd). F_GET_SEALS will only succeed for memfds (or rather
++ * for shmem files), and we want to be sure it's actually sealed.
++ */
++static int is_self_cloned(void)
++{
++ int fd, ret, is_cloned = 0;
++
++ fd = open("/proc/self/exe", O_RDONLY|O_CLOEXEC);
++ if (fd < 0)
++ return -ENOTRECOVERABLE;
++
++#ifdef HAVE_MEMFD_CREATE
++ ret = fcntl(fd, F_GET_SEALS);
++ is_cloned = (ret == RUNC_MEMFD_SEALS);
++#else
++ struct stat statbuf = {0};
++ ret = fstat(fd, &statbuf);
++ if (ret >= 0)
++ is_cloned = (statbuf.st_nlink == 0);
++#endif
++ close(fd);
++ return is_cloned;
++}
++
++/*
++ * Basic wrapper around mmap(2) that gives you the file length so you can
++ * safely treat it as an ordinary buffer. Only gives you read access.
++ */
++static char *read_file(char *path, size_t *length)
++{
++ int fd;
++ char buf[4096], *copy = NULL;
++
++ if (!length)
++ return NULL;
++
++ fd = open(path, O_RDONLY | O_CLOEXEC);
++ if (fd < 0)
++ return NULL;
++
++ *length = 0;
++ for (;;) {
++ int n;
++
++ n = read(fd, buf, sizeof(buf));
++ if (n < 0)
++ goto error;
++ if (!n)
++ break;
++
++ copy = must_realloc(copy, (*length + n) * sizeof(*copy));
++ memcpy(copy + *length, buf, n);
++ *length += n;
++ }
++ close(fd);
++ return copy;
++
++error:
++ close(fd);
++ free(copy);
++ return NULL;
++}
++
++/*
++ * A poor-man's version of "xargs -0". Basically parses a given block of
++ * NUL-delimited data, within the given length and adds a pointer to each entry
++ * to the array of pointers.
++ */
++static int parse_xargs(char *data, int data_length, char ***output)
++{
++ int num = 0;
++ char *cur = data;
++
++ if (!data || *output != NULL)
++ return -1;
++
++ while (cur < data + data_length) {
++ num++;
++ *output = must_realloc(*output, (num + 1) * sizeof(**output));
++ (*output)[num - 1] = cur;
++ cur += strlen(cur) + 1;
++ }
++ (*output)[num] = NULL;
++ return num;
++}
++
++/*
++ * "Parse" out argv and envp from /proc/self/cmdline and /proc/self/environ.
++ * This is necessary because we are running in a context where we don't have a
++ * main() that we can just get the arguments from.
++ */
++static int fetchve(char ***argv, char ***envp)
++{
++ char *cmdline = NULL, *environ = NULL;
++ size_t cmdline_size, environ_size;
++
++ cmdline = read_file("/proc/self/cmdline", &cmdline_size);
++ if (!cmdline)
++ goto error;
++ environ = read_file("/proc/self/environ", &environ_size);
++ if (!environ)
++ goto error;
++
++ if (parse_xargs(cmdline, cmdline_size, argv) <= 0)
++ goto error;
++ if (parse_xargs(environ, environ_size, envp) <= 0)
++ goto error;
++
++ return 0;
++
++error:
++ free(environ);
++ free(cmdline);
++ return -EINVAL;
++}
++
++static int clone_binary(void)
++{
++ int binfd, memfd;
++ ssize_t sent = 0;
++
++#ifdef HAVE_MEMFD_CREATE
++ memfd = memfd_create(RUNC_MEMFD_COMMENT, MFD_CLOEXEC | MFD_ALLOW_SEALING);
++#else
++ memfd = open("/tmp", O_TMPFILE | O_EXCL | O_RDWR | O_CLOEXEC, 0711);
++#endif
++ if (memfd < 0)
++ return -ENOTRECOVERABLE;
++
++ binfd = open("/proc/self/exe", O_RDONLY | O_CLOEXEC);
++ if (binfd < 0)
++ goto error;
++
++ sent = sendfile(memfd, binfd, NULL, RUNC_SENDFILE_MAX);
++ close(binfd);
++ if (sent < 0)
++ goto error;
++
++#ifdef HAVE_MEMFD_CREATE
++ int err = fcntl(memfd, F_ADD_SEALS, RUNC_MEMFD_SEALS);
++ if (err < 0)
++ goto error;
++#else
++ /* Need to re-open "memfd" as read-only to avoid execve(2) giving -EXTBUSY. */
++ int newfd;
++ char *fdpath = NULL;
++
++ if (asprintf(&fdpath, "/proc/self/fd/%d", memfd) < 0)
++ goto error;
++ newfd = open(fdpath, O_RDONLY | O_CLOEXEC);
++ free(fdpath);
++ if (newfd < 0)
++ goto error;
++
++ close(memfd);
++ memfd = newfd;
++#endif
++ return memfd;
++
++error:
++ close(memfd);
++ return -EIO;
++}
++
++int ensure_cloned_binary(void)
++{
++ int execfd;
++ char **argv = NULL, **envp = NULL;
++
++ /* Check that we're not self-cloned, and if we are then bail. */
++ int cloned = is_self_cloned();
++ if (cloned > 0 || cloned == -ENOTRECOVERABLE)
++ return cloned;
++
++ if (fetchve(&argv, &envp) < 0)
++ return -EINVAL;
++
++ execfd = clone_binary();
++ if (execfd < 0)
++ return -EIO;
++
++ fexecve(execfd, argv, envp);
++ return -ENOEXEC;
++}
+diff --git a/libcontainer/nsenter/nsexec.c b/libcontainer/nsenter/nsexec.c
+index 28269dfc0..7750af35e 100644
+--- a/libcontainer/nsenter/nsexec.c
++++ b/libcontainer/nsenter/nsexec.c
+@@ -534,6 +534,9 @@ void join_namespaces(char *nslist)
+ free(namespaces);
+ }
+
++/* Defined in cloned_binary.c. */
++extern int ensure_cloned_binary(void);
++
+ void nsexec(void)
+ {
+ int pipenum;
+@@ -549,6 +552,14 @@ void nsexec(void)
+ if (pipenum == -1)
+ return;
+
++ /*
++ * We need to re-exec if we are not in a cloned binary. This is necessary
++ * to ensure that containers won't be able to access the host binary
++ * through /proc/self/exe. See CVE-2019-5736.
++ */
++ if (ensure_cloned_binary() < 0)
++ bail("could not ensure we are a cloned binary");
++
+ /* Parse all of the netlink configuration. */
+ nl_parse(pipenum, &config);
+
diff --git a/gnu/packages/virtualization.scm b/gnu/packages/virtualization.scm
index f5e4540329..8a5af2e8ea 100644
--- a/gnu/packages/virtualization.scm
+++ b/gnu/packages/virtualization.scm
@@ -847,15 +847,17 @@ monitor/GPU.")
(define-public runc
(package
(name "runc")
- (version "1.0.0-rc5")
+ (version "1.0.0-rc6")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/opencontainers/runc/releases/"
"download/v" version "/runc.tar.xz"))
+ (file-name (string-append name "-" version ".tar.xz"))
+ (patches (search-patches "runc-CVE-2019-5736.patch"))
(sha256
(base32
- "081avdzwnqpk368wbaihlzsypaxpj42d7699h7jgp0fks14x4103"))))
+ "1c7832dq70slkjh8qp2civ1wxhhdd2hrx84pq7db1mmqc9fdr3cc"))))
(build-system go-build-system)
(arguments
'(#:import-path "github.com/opencontainers/runc"
generated by cgit v1.2.3 (git 2.45.0) at 2024-11-20 12:41:36 +0000