A client that opens a socket but does not negotiate is merely hogging
qemu's resources (an open fd and a small amount of memory); and a
malicious client that can access the port where NBD is listening can
attempt a denial of service attack by intentionally opening and
abandoning lots of unfinished connections.  The previous patch put a
default bound on the number of such ongoing connections, but once that
limit is hit, no more clients can connect (including legitimate ones).
The solution is to insist that clients complete handshake within a
reasonable time limit, defaulting to 10 seconds.  A client that has
not successfully completed NBD_OPT_GO by then (including the case of
where the client didn't know TLS credentials to even reach the point
of NBD_OPT_GO) is wasting our time and does not deserve to stay
connected.  Later patches will allow fine-tuning the limit away from
the default value (including disabling it for doing integration
testing of the handshake process itself).

Note that this patch in isolation actually makes it more likely to see
qemu SEGV after nbd-server-stop, as any client socket still connected
when the server shuts down will now be closed after 10 seconds rather
than at the client's whims.  That will be addressed in the next patch.

For a demo of this patch in action:
$ qemu-nbd -f raw -r -t -e 10 file &
$ nbdsh --opt-mode -c '
H = list()
for i in range(20):
  print(i)
  H.insert(i, nbd.NBD())
  H[i].set_opt_mode(True)
  H[i].connect_uri("nbd://localhost")
'

where later connections get to start progressing once earlier ones are
forcefully dropped for taking too long, rather than hanging.

Suggested-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Eric Blake <eblake@redhat.com>
---
 nbd/server.c     | 31 ++++++++++++++++++++++++++++++-
 nbd/trace-events |  1 +
 2 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/nbd/server.c b/nbd/server.c
index 31b77bf0d4f..a470052d957 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -132,6 +132,7 @@ struct NBDClient {
     QCryptoTLSCreds *tlscreds;
     char *tlsauthz;
     uint32_t handshake_limit;
+    QEMUTimer *handshake_timer;
     QIOChannelSocket *sioc; /* The underlying data channel */
     QIOChannel *ioc; /* The current I/O channel which may differ (eg TLS) */

@@ -3186,6 +3187,14 @@ static void nbd_client_receive_next_request(NBDClient *client)
     }
 }

+static void nbd_handshake_timer_cb(void *opaque)
+{
+    QIOChannel *ioc = opaque;
+
+    trace_nbd_handshake_timer_cb();
+    qio_channel_shutdown(ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
+}
+
 static coroutine_fn void nbd_co_client_start(void *opaque)
 {
     NBDClient *client = opaque;
@@ -3193,15 +3202,35 @@ static coroutine_fn void nbd_co_client_start(void *opaque)

     qemu_co_mutex_init(&client->send_lock);

-    /* TODO - utilize client->handshake_limit */
+    /*
+     * Create a timer to bound the time spent in negotiation. If the
+     * timer expires, it is likely nbd_negotiate will fail because the
+     * socket was shutdown.
+     */
+    client->handshake_timer = aio_timer_new(qemu_get_aio_context(),
+                                            QEMU_CLOCK_REALTIME,
+                                            SCALE_NS,
+                                            nbd_handshake_timer_cb,
+                                            client->sioc);
+    if (client->handshake_limit > 0) {
+        timer_mod(client->handshake_timer,
+                  qemu_clock_get_ns(QEMU_CLOCK_REALTIME) +
+                  client->handshake_limit * NANOSECONDS_PER_SECOND);
+    }
+
     if (nbd_negotiate(client, &local_err)) {
         if (local_err) {
             error_report_err(local_err);
         }
+        timer_free(client->handshake_timer);
+        client->handshake_timer = NULL;
         client_close(client, false);
         return;
     }

+    timer_free(client->handshake_timer);
+    client->handshake_timer = NULL;
+
     WITH_QEMU_LOCK_GUARD(&client->lock) {
         nbd_client_receive_next_request(client);
     }
diff --git a/nbd/trace-events b/nbd/trace-events
index 00ae3216a11..cbd0a4ab7e4 100644
--- a/nbd/trace-events
+++ b/nbd/trace-events
@@ -76,6 +76,7 @@ nbd_co_receive_request_payload_received(uint64_t cookie, uint64_t len) "Payload
 nbd_co_receive_ext_payload_compliance(uint64_t from, uint64_t len) "client sent non-compliant write without payload flag: from=0x%" PRIx64 ", len=0x%" PRIx64
 nbd_co_receive_align_compliance(const char *op, uint64_t from, uint64_t len, uint32_t align) "client sent non-compliant unaligned %s request: from=0x%" PRIx64 ", len=0x%" PRIx64 ", align=0x%" PRIx32
 nbd_trip(void) "Reading request"
+nbd_handshake_timer_cb(void) "client took too long to negotiate"

 # client-connection.c
 nbd_connect_thread_sleep(uint64_t timeout) "timeout %" PRIu64
-- 
2.45.2

On Wed, Aug 07, 2024 at 12:43:30PM -0500, Eric Blake wrote:
> A client that opens a socket but does not negotiate is merely hogging
> qemu's resources (an open fd and a small amount of memory); and a
> malicious client that can access the port where NBD is listening can
> attempt a denial of service attack by intentionally opening and
> abandoning lots of unfinished connections.  The previous patch put a
> default bound on the number of such ongoing connections, but once that
> limit is hit, no more clients can connect (including legitimate ones).
> The solution is to insist that clients complete handshake within a
> reasonable time limit, defaulting to 10 seconds.  A client that has
> not successfully completed NBD_OPT_GO by then (including the case of
> where the client didn't know TLS credentials to even reach the point
> of NBD_OPT_GO) is wasting our time and does not deserve to stay
> connected.  Later patches will allow fine-tuning the limit away from
> the default value (including disabling it for doing integration
> testing of the handshake process itself).
> 
> Note that this patch in isolation actually makes it more likely to see
> qemu SEGV after nbd-server-stop, as any client socket still connected
> when the server shuts down will now be closed after 10 seconds rather
> than at the client's whims.  That will be addressed in the next patch.
> 
> For a demo of this patch in action:
> $ qemu-nbd -f raw -r -t -e 10 file &
> $ nbdsh --opt-mode -c '
> H = list()
> for i in range(20):
>   print(i)
>   H.insert(i, nbd.NBD())
>   H[i].set_opt_mode(True)
>   H[i].connect_uri("nbd://localhost")
> '
> 
> where later connections get to start progressing once earlier ones are
> forcefully dropped for taking too long, rather than hanging.
> 
> Suggested-by: Daniel P. Berrangé <berrange@redhat.com>
> Signed-off-by: Eric Blake <eblake@redhat.com>
> ---
>  nbd/server.c     | 31 ++++++++++++++++++++++++++++++-
>  nbd/trace-events |  1 +
>  2 files changed, 31 insertions(+), 1 deletion(-)

Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>


With regards,
Daniel
-- 
|: https://berrange.com      -o-    https://www.flickr.com/photos/dberrange :|
|: https://libvirt.org         -o-            https://fstop138.berrange.com :|
|: https://entangle-photo.org    -o-    https://www.instagram.com/dberrange :|