On Mon, Mar 17, 2025 at 10:52:24AM +0100, Michal Luczaj wrote:

Racing signal-interrupted connect() and sockmap update may result in an unconnected (and missing vsock transport) socket in a sockmap.

Test spends 2 seconds attempting to reach WARN_ON_ONCE().

connect / state = SS_CONNECTED / sock_map_update_elem if signal_pending state = SS_UNCONNECTED

connect transport = NULL vsock_bpf_recvmsg WARN_ON_ONCE(!vsk->transport)

Signed-off-by: Michal Luczaj mhal@rbox.co

.../selftests/bpf/prog_tests/sockmap_basic.c | 99 ++++++++++++++++++++++ 1 file changed, 99 insertions(+)

LGTM for the vsock part!

Acked-by: Stefano Garzarella sgarzare@redhat.com

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 1e3e4392dcca0e1722c1982ecc649a80c27443b2..2f8bba27866354848f1e30b5473cedb6a85244ff 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -3,6 +3,7 @@ #include <error.h> #include <netinet/tcp.h> #include <sys/epoll.h> +#include <linux/time64.h>

#include "test_progs.h" #include "test_skmsg_load_helpers.skel.h" @@ -1042,6 +1043,102 @@ static void test_sockmap_vsock_unconnected(void) xclose(map); }

+#define CONNECT_SIGNAL_RACE_TIMEOUT 2 /* seconds */

+static void sig_handler(int signum) +{

• /* nop */

+}

+static void connect_signal_racer_cleanup(void *map) +{

• xclose(*(int *)map);

+}

+static void *connect_signal_racer(void *arg) +{

• pid_t pid;
• int map;
• map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int),

• 	     sizeof(int), 1, NULL);
  

• if (!ASSERT_OK_FD(map, "bpf_map_create"))

• return NULL;
  

• pthread_cleanup_push(connect_signal_racer_cleanup, &map);
• pid = getpid();
• for (;;) {

• int c = *(int *)arg;
  

• int zero = 0;
  

• (void)bpf_map_update_elem(map, &zero, &c, BPF_ANY);
  

• if (kill(pid, SIGUSR1)) {
  

• 	FAIL_ERRNO("kill");
  

• 	break;
  

• }
  

• if ((recv(c, NULL, 0, MSG_DONTWAIT) < 0) && errno == ENODEV) {
  

• 	FAIL_ERRNO("recv");
  

• 	break;
  

• }
  

• }
• pthread_cleanup_pop(1);
• return NULL;

+}

+static void test_sockmap_vsock_connect_signal_race(void) +{

• struct sockaddr_vm addr, bad_addr;
• socklen_t alen = sizeof(addr);
• sighandler_t orig_handler;
• pthread_t thread;
• int s, c, p;
• __u64 tout;
• orig_handler = signal(SIGUSR1, sig_handler);
• if (!ASSERT_NEQ(orig_handler, SIG_ERR, "signal handler setup"))

• return;
  

• s = socket_loopback(AF_VSOCK, SOCK_SEQPACKET | SOCK_NONBLOCK);
• if (s < 0)

• goto restore;
  

• if (xgetsockname(s, (struct sockaddr *)&addr, &alen))

• goto close;
  

• bad_addr = addr;
• bad_addr.svm_cid = 0x42424242; /* non-existing */
• if (xpthread_create(&thread, 0, connect_signal_racer, &c))

• goto close;
  

• tout = get_time_ns() + CONNECT_SIGNAL_RACE_TIMEOUT * NSEC_PER_SEC;
• do {

• c = xsocket(AF_VSOCK, SOCK_SEQPACKET, 0);
  

• if (c < 0)
  

• 	break;
  

• if (connect(c, (struct sockaddr *)&addr, alen) && errno == EINTR)
  

• 	(void)connect(c, (struct sockaddr *)&bad_addr, alen);
  

• xclose(c);
  

• p = accept(s, NULL, NULL);
  

• if (p >= 0)
  

• 	xclose(p);
  

• } while (get_time_ns() < tout);
• ASSERT_OK(pthread_cancel(thread), "pthread_cancel");
• xpthread_join(thread, NULL);

+close:

• xclose(s);

+restore:

• ASSERT_NEQ(signal(SIGUSR1, orig_handler), SIG_ERR, "handler restore");

+}

void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -1108,4 +1205,6 @@ void test_sockmap_basic(void) test_sockmap_skb_verdict_vsock_poll(); if (test__start_subtest("sockmap vsock unconnected")) test_sockmap_vsock_unconnected();

• if (test__start_subtest("sockmap vsock connect signal race"))

• test_sockmap_vsock_connect_signal_race();
  

}

-- 2.48.1

On Mon, Mar 17, 2025 at 10:52:25AM +0100, Michal Luczaj wrote:

Signal delivery during connect() may lead to a disconnect of an already established socket. That involves removing socket from any sockmap and resetting state to SS_UNCONNECTED. While it correctly restores socket's proto, a call to vsock_bpf_recvmsg() might have been already under way in another thread. If the connect()ing thread reassigns the vsock transport to NULL, the recvmsg()ing thread may trigger a WARN_ON_ONCE.

connect / state = SS_CONNECTED / sock_map_update_elem vsock_bpf_recvmsg psock = sk_psock_get() lock sk if signal_pending unhash sock_map_remove_links state = SS_UNCONNECTED release sk

connect transport = NULL lock sk WARN_ON_ONCE(!vsk->transport)

Protect recvmsg() from racing against transport reassignment. Enforce the sockmap invariant that psock implies transport: lock socket before getting psock.

WARNING: CPU: 9 PID: 1222 at net/vmw_vsock/vsock_bpf.c:92 vsock_bpf_recvmsg+0xb55/0xe00 CPU: 9 UID: 0 PID: 1222 Comm: a.out Not tainted 6.14.0-rc5+ RIP: 0010:vsock_bpf_recvmsg+0xb55/0xe00 sock_recvmsg+0x1b2/0x220 __sys_recvfrom+0x190/0x270 __x64_sys_recvfrom+0xdc/0x1b0 do_syscall_64+0x93/0x1b0 entry_SYSCALL_64_after_hwframe+0x76/0x7e

Fixes: 634f1a7110b4 ("vsock: support sockmap") Signed-off-by: Michal Luczaj mhal@rbox.co

---

net/vmw_vsock/vsock_bpf.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index c68fdaf09046b68254dac3ea70ffbe73dfa45cef..5138195d91fb258d4bc09b48e80e13651d62863a 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -73,28 +73,35 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int return err; }

-static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg,

• 	     size_t len, int flags, int *addr_len)
  

+static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,

• 	     int flags, int *addr_len)
  

I would avoid this change, especially in a patch with the Fixes tag then to be backported.

{ struct sk_psock *psock; struct vsock_sock *vsk; int copied;

• /* Since signal delivery during connect() may reset the state of socket

• * that's already in a sockmap, take the lock before checking on psock.
  

• * This serializes a possible transport reassignment, protecting this
  

• * function from running with NULL transport.
  

• */
  

• lock_sock(sk);
• psock = sk_psock_get(sk);

• if (unlikely(!psock))

• if (unlikely(!psock)) {

• release_sock(sk);
  

  return __vsock_recvmsg(sk, msg, len, flags);
• }

• lock_sock(sk); vsk = vsock_sk(sk);

• if (WARN_ON_ONCE(!vsk->transport)) { copied = -ENODEV; goto out; }

  if (vsock_has_data(sk, psock) && sk_psock_queue_empty(psock)) {

• release_sock(sk);
  

  sk_psock_put(sk, psock);

• release_sock(sk);
  

But here we release it, so can still a reset happen at this point, before calling __vsock_connectible_recvmsg(). In there anyway we handle the case where transport is null, so there's no problem, right?

The rest LTGM.

Thanks, Stefano

return __vsock_recvmsg(sk, msg, len, flags);

}

@@ -108,8 +115,8 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, }

if (sk_psock_queue_empty(psock)) {

• 	release_sock(sk);
  sk_psock_put(sk, psock);
  

• 	release_sock(sk);
  return __vsock_recvmsg(sk, msg, len, flags);
  

  }

@@ -117,8 +124,8 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, }

out:

• release_sock(sk); sk_psock_put(sk, psock);

• release_sock(sk);

  return copied;

}

-- 2.48.1