passt/util.h
Stefano Brivio 0515adceaa passt, pasta: Namespace-based sandboxing, defer seccomp policy application
To reach (at least) a conceptually equivalent security level as
implemented by --enable-sandbox in slirp4netns, we need to create a
new mount namespace and pivot_root() into a new (empty) mountpoint, so
that passt and pasta can't access any filesystem resource after
initialisation.

While at it, also detach IPC, PID (only for passt, to prevent
vulnerabilities based on the knowledge of a target PID), and UTS
namespaces.

With this approach, if we apply the seccomp filters right after the
configuration step, the number of allowed syscalls grows further. To
prevent this, defer the application of seccomp policies after the
initialisation phase, before the main loop, that's where we expect bad
things to happen, potentially. This way, we get back to 22 allowed
syscalls for passt and 34 for pasta, on x86_64.

While at it, move #syscalls notes to specific code paths wherever it
conceptually makes sense.

We have to open all the file handles we'll ever need before
sandboxing:

- the packet capture file can only be opened once, drop instance
  numbers from the default path and use the (pre-sandbox) PID instead

- /proc/net/tcp{,v6} and /proc/net/udp{,v6}, for automatic detection
  of bound ports in pasta mode, are now opened only once, before
  sandboxing, and their handles are stored in the execution context

- the UNIX domain socket for passt is also bound only once, before
  sandboxing: to reject clients after the first one, instead of
  closing the listening socket, keep it open, accept and immediately
  discard new connection if we already have a valid one

Clarify the (unchanged) behaviour for --netns-only in the man page.

To actually make passt and pasta processes run in a separate PID
namespace, we need to unshare(CLONE_NEWPID) before forking to
background (if configured to do so). Introduce a small daemon()
implementation, __daemon(), that additionally saves the PID file
before forking. While running in foreground, the process itself can't
move to a new PID namespace (a process can't change the notion of its
own PID): mention that in the man page.

For some reason, fork() in a detached PID namespace causes SIGTERM
and SIGQUIT to be ignored, even if the handler is still reported as
SIG_DFL: add a signal handler that just exits.

We can now drop most of the pasta_child_handler() implementation,
that took care of terminating all processes running in the same
namespace, if pasta started a shell: the shell itself is now the
init process in that namespace, and all children will terminate
once the init process exits.

Issuing 'echo $$' in a detached PID namespace won't return the
actual namespace PID as seen from the init namespace: adapt
demo and test setup scripts to reflect that.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2022-02-21 13:41:13 +01:00

216 lines
5.1 KiB
C

/* SPDX-License-Identifier: AGPL-3.0-or-later
* Copyright (c) 2021 Red Hat GmbH
* Author: Stefano Brivio <sbrivio@redhat.com>
*/
void err(const char *format, ...);
void warn(const char *format, ...);
void info(const char *format, ...);
void debug(const char *format, ...);
#ifndef SECCOMP_RET_KILL_PROCESS
#define SECCOMP_RET_KILL_PROCESS SECCOMP_RET_KILL
#endif
#ifndef ETH_MAX_MTU
#define ETH_MAX_MTU USHRT_MAX
#endif
#ifndef ETH_MIN_MTU
#define ETH_MIN_MTU 68
#endif
#define CHECK_SET_MIN_MAX(basename, fd) \
do { \
if ((fd) < basename##min) \
basename##min = (fd); \
if ((fd) > basename##max) \
basename##max = (fd); \
} while (0)
#define CHECK_SET_MIN_MAX_PROTO_FD(proto, ipproto, proto_ctx, fd) \
do { \
if ((proto) == (ipproto)) \
CHECK_SET_MIN_MAX(c->proto_ctx.fd_, (fd)); \
} while (0)
#ifndef MIN
#define MIN(x, y) (((x) < (y)) ? (x) : (y))
#endif
#ifndef MAX
#define MAX(x, y) (((x) > (y)) ? (x) : (y))
#endif
#define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
#define ROUND_DOWN(x, y) ((x) & ~((y) - 1))
#define ROUND_UP(x, y) (((x) + (y) - 1) & ~((y) - 1))
#define BITMAP_BIT(n) (1UL << (n) % (sizeof(long) * 8))
#define BITMAP_WORD(n) (n / (sizeof(long) * 8))
#define SWAP(a, b) \
do { \
__typeof__(a) __x = (a); (a) = (b); (b) = __x; \
} while (0) \
#define STRINGIFY(x) #x
#define STR(x) STRINGIFY(x)
#ifdef P_tmpdir
#define TMPDIR P_tmpdir
#else
#define TMPDIR "/tmp"
#endif
#define V4 0
#define V6 1
#define IP_VERSIONS 2
enum {
IP_VERSION_DISABLED = 0,
IP_VERSION_ENABLED,
IP_VERSION_PROBE,
};
#define ARRAY_SIZE(a) ((int)(sizeof(a) / sizeof((a)[0])))
#define IN_INTERVAL(a, b, x) ((x) >= (a) && (x) <= (b))
#define FD_PROTO(x, proto) \
(IN_INTERVAL(c->proto.fd_min, c->proto.fd_max, (x)))
#define PORT_EPHEMERAL_MIN ((1 << 15) + (1 << 14)) /* RFC 6335 */
#define PORT_IS_EPHEMERAL(port) ((port) >= PORT_EPHEMERAL_MIN)
#define MAC_ZERO ((uint8_t [ETH_ALEN]){ 0 })
#define MAC_IS_ZERO(addr) (!memcmp((addr), MAC_ZERO, ETH_ALEN))
#define NS_FN_STACK_SIZE (RLIMIT_STACK_VAL * 1024 / 4)
#define NS_CALL(fn, arg) \
do { \
char ns_fn_stack[NS_FN_STACK_SIZE]; \
\
clone((fn), ns_fn_stack + sizeof(ns_fn_stack) / 2, \
CLONE_VM | CLONE_VFORK | CLONE_FILES | SIGCHLD, \
(void *)(arg)); \
} while (0)
#if __BYTE_ORDER == __BIG_ENDIAN
#define L2_BUF_ETH_IP4_INIT \
{ \
.h_dest = { 0 }, \
.h_source = { 0 }, \
.h_proto = ETH_P_IP, \
}
#else
#define L2_BUF_ETH_IP4_INIT \
{ \
.h_dest = { 0 }, \
.h_source = { 0 }, \
.h_proto = __bswap_constant_16(ETH_P_IP), \
}
#endif
#if __BYTE_ORDER == __BIG_ENDIAN
#define L2_BUF_ETH_IP6_INIT \
{ \
.h_dest = { 0 }, \
.h_source = { 0 }, \
.h_proto = ETH_P_IPV6, \
}
#else
#define L2_BUF_ETH_IP6_INIT \
{ \
.h_dest = { 0 }, \
.h_source = { 0 }, \
.h_proto = __bswap_constant_16(ETH_P_IPV6), \
}
#endif
#define L2_BUF_IP4_INIT(proto) \
{ \
.version = 4, \
.ihl = 5, \
.tos = 0, \
.tot_len = 0, \
.id = 0, \
.frag_off = 0, \
.ttl = 255, \
.protocol = (proto), \
.saddr = 0, \
.daddr = 0, \
}
#define L2_BUF_IP6_INIT(proto) \
{ \
.priority = 0, \
.version = 6, \
.flow_lbl = { 0 }, \
.payload_len = 0, \
.nexthdr = (proto), \
.hop_limit = 255, \
.saddr = IN6ADDR_ANY_INIT, \
.daddr = IN6ADDR_ANY_INIT, \
}
#define RCVBUF_BIG (2UL * 1024 * 1024)
#define SNDBUF_BIG (4UL * 1024 * 1024)
#define SNDBUF_SMALL (128UL * 1024)
#include <net/if.h>
#include <limits.h>
#include <stdarg.h>
enum bind_type {
BIND_ANY = 0,
BIND_LOOPBACK,
BIND_LL,
BIND_EXT,
};
struct ctx;
struct ipv6hdr {
#pragma GCC diagnostic ignored "-Wpedantic"
#if __BYTE_ORDER == __BIG_ENDIAN
__u8 version:4,
priority:4;
#else
uint8_t priority:4,
version:4;
#endif
#pragma GCC diagnostic pop
uint8_t flow_lbl[3];
__be16 payload_len;
__u8 nexthdr;
__u8 hop_limit;
struct in6_addr saddr;
struct in6_addr daddr;
};
struct ipv6_opt_hdr {
__u8 nexthdr;
__u8 hdrlen;
/*
* TLV encoded option data follows.
*/
} __attribute__((packed)); /* required for some archs */
__attribute__ ((weak)) int ffsl(long int i) { return __builtin_ffsl(i); }
void __openlog(const char *ident, int option, int facility);
void passt_vsyslog(int pri, const char *format, va_list ap);
void __setlogmask(int mask);
char *ipv6_l4hdr(struct ipv6hdr *ip6h, uint8_t *proto);
int sock_l4(struct ctx *c, int af, uint8_t proto, uint16_t port,
enum bind_type bind_addr, uint32_t data);
void sock_probe_mem(struct ctx *c);
int timespec_diff_ms(struct timespec *a, struct timespec *b);
void bitmap_set(uint8_t *map, int bit);
void bitmap_clear(uint8_t *map, int bit);
int bitmap_isset(const uint8_t *map, int bit);
char *line_read(char *buf, size_t len, int fd);
void procfs_scan_listen(struct ctx *c, uint8_t proto, int ip_version, int ns,
uint8_t *map, uint8_t *exclude);
void drop_caps(void);
int ns_enter(struct ctx *c);
void write_pidfile(int fd, pid_t pid);
int __daemon(int pidfile_fd, int devnull_fd);