summaryrefslogtreecommitdiff
path: root/net/vmw_vsock/af_vsock.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/vmw_vsock/af_vsock.c')
-rw-r--r--net/vmw_vsock/af_vsock.c104
1 files changed, 90 insertions, 14 deletions
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index b52b798aa4c2..ef519b55a3d9 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -337,7 +337,10 @@ EXPORT_SYMBOL_GPL(vsock_find_connected_socket);
void vsock_remove_sock(struct vsock_sock *vsk)
{
- vsock_remove_bound(vsk);
+ /* Transport reassignment must not remove the binding. */
+ if (sock_flag(sk_vsock(vsk), SOCK_DEAD))
+ vsock_remove_bound(vsk);
+
vsock_remove_connected(vsk);
}
EXPORT_SYMBOL_GPL(vsock_remove_sock);
@@ -404,6 +407,8 @@ EXPORT_SYMBOL_GPL(vsock_enqueue_accept);
static bool vsock_use_local_transport(unsigned int remote_cid)
{
+ lockdep_assert_held(&vsock_register_mutex);
+
if (!transport_local)
return false;
@@ -461,6 +466,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
remote_flags = vsk->remote_addr.svm_flags;
+ mutex_lock(&vsock_register_mutex);
+
switch (sk->sk_type) {
case SOCK_DGRAM:
new_transport = transport_dgram;
@@ -476,12 +483,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
new_transport = transport_h2g;
break;
default:
- return -ESOCKTNOSUPPORT;
+ ret = -ESOCKTNOSUPPORT;
+ goto err;
}
if (vsk->transport) {
- if (vsk->transport == new_transport)
- return 0;
+ if (vsk->transport == new_transport) {
+ ret = 0;
+ goto err;
+ }
/* transport->release() must be called with sock lock acquired.
* This path can only be taken during vsock_connect(), where we
@@ -491,13 +501,30 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
*/
vsk->transport->release(vsk);
vsock_deassign_transport(vsk);
+
+ /* transport's release() and destruct() can touch some socket
+ * state, since we are reassigning the socket to a new transport
+ * during vsock_connect(), let's reset these fields to have a
+ * clean state.
+ */
+ sock_reset_flag(sk, SOCK_DONE);
+ sk->sk_state = TCP_CLOSE;
+ vsk->peer_shutdown = 0;
}
/* We increase the module refcnt to prevent the transport unloading
* while there are open sockets assigned to it.
*/
- if (!new_transport || !try_module_get(new_transport->module))
- return -ENODEV;
+ if (!new_transport || !try_module_get(new_transport->module)) {
+ ret = -ENODEV;
+ goto err;
+ }
+
+ /* It's safe to release the mutex after a successful try_module_get().
+ * Whichever transport `new_transport` points at, it won't go away until
+ * the last module_put() below or in vsock_deassign_transport().
+ */
+ mutex_unlock(&vsock_register_mutex);
if (sk->sk_type == SOCK_SEQPACKET) {
if (!new_transport->seqpacket_allow ||
@@ -516,12 +543,31 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
vsk->transport = new_transport;
return 0;
+err:
+ mutex_unlock(&vsock_register_mutex);
+ return ret;
}
EXPORT_SYMBOL_GPL(vsock_assign_transport);
+/*
+ * Provide safe access to static transport_{h2g,g2h,dgram,local} callbacks.
+ * Otherwise we may race with module removal. Do not use on `vsk->transport`.
+ */
+static u32 vsock_registered_transport_cid(const struct vsock_transport **transport)
+{
+ u32 cid = VMADDR_CID_ANY;
+
+ mutex_lock(&vsock_register_mutex);
+ if (*transport)
+ cid = (*transport)->get_local_cid();
+ mutex_unlock(&vsock_register_mutex);
+
+ return cid;
+}
+
bool vsock_find_cid(unsigned int cid)
{
- if (transport_g2h && cid == transport_g2h->get_local_cid())
+ if (cid == vsock_registered_transport_cid(&transport_g2h))
return true;
if (transport_h2g && cid == VMADDR_CID_HOST)
@@ -643,7 +689,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
unsigned int i;
for (i = 0; i < MAX_PORT_RETRIES; i++) {
- if (port <= LAST_RESERVED_PORT)
+ if (port == VMADDR_PORT_ANY ||
+ port <= LAST_RESERVED_PORT)
port = LAST_RESERVED_PORT + 1;
new_addr.svm_port = port++;
@@ -812,6 +859,13 @@ static void __vsock_release(struct sock *sk, int level)
*/
lock_sock_nested(sk, level);
+ /* Indicate to vsock_remove_sock() that the socket is being released and
+ * can be removed from the bound_table. Unlike transport reassignment
+ * case, where the socket must remain bound despite vsock_remove_sock()
+ * being called from the transport release() callback.
+ */
+ sock_set_flag(sk, SOCK_DEAD);
+
if (vsk->transport)
vsk->transport->release(vsk);
else if (sock_type_connectible(sk->sk_type))
@@ -870,6 +924,9 @@ EXPORT_SYMBOL_GPL(vsock_create_connected);
s64 vsock_stream_has_data(struct vsock_sock *vsk)
{
+ if (WARN_ON(!vsk->transport))
+ return 0;
+
return vsk->transport->stream_has_data(vsk);
}
EXPORT_SYMBOL_GPL(vsock_stream_has_data);
@@ -878,6 +935,9 @@ s64 vsock_connectible_has_data(struct vsock_sock *vsk)
{
struct sock *sk = sk_vsock(vsk);
+ if (WARN_ON(!vsk->transport))
+ return 0;
+
if (sk->sk_type == SOCK_SEQPACKET)
return vsk->transport->seqpacket_has_data(vsk);
else
@@ -887,6 +947,9 @@ EXPORT_SYMBOL_GPL(vsock_connectible_has_data);
s64 vsock_stream_has_space(struct vsock_sock *vsk)
{
+ if (WARN_ON(!vsk->transport))
+ return 0;
+
return vsk->transport->stream_has_space(vsk);
}
EXPORT_SYMBOL_GPL(vsock_stream_has_space);
@@ -1161,6 +1224,9 @@ static int vsock_read_skb(struct sock *sk, skb_read_actor_t read_actor)
{
struct vsock_sock *vsk = vsock_sk(sk);
+ if (WARN_ON_ONCE(!vsk->transport))
+ return -ENODEV;
+
return vsk->transport->read_skb(vsk, read_actor);
}
@@ -1501,6 +1567,11 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
if (err < 0)
goto out;
+ /* sk_err might have been set as a result of an earlier
+ * (failed) connect attempt.
+ */
+ sk->sk_err = 0;
+
/* Mark sock as connecting and set the error code to in
* progress in case this is a non-blocking connect.
*/
@@ -1515,7 +1586,11 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
timeout = vsk->connect_timeout;
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- while (sk->sk_state != TCP_ESTABLISHED && sk->sk_err == 0) {
+ /* If the socket is already closing or it is in an error state, there
+ * is no point in waiting.
+ */
+ while (sk->sk_state != TCP_ESTABLISHED &&
+ sk->sk_state != TCP_CLOSING && sk->sk_err == 0) {
if (flags & O_NONBLOCK) {
/* If we're not going to block, we schedule a timeout
* function to generate a timeout on the connection
@@ -2462,18 +2537,19 @@ static long vsock_dev_do_ioctl(struct file *filp,
unsigned int cmd, void __user *ptr)
{
u32 __user *p = ptr;
- u32 cid = VMADDR_CID_ANY;
int retval = 0;
+ u32 cid;
switch (cmd) {
case IOCTL_VM_SOCKETS_GET_LOCAL_CID:
/* To be compatible with the VMCI behavior, we prioritize the
* guest CID instead of well-know host CID (VMADDR_CID_HOST).
*/
- if (transport_g2h)
- cid = transport_g2h->get_local_cid();
- else if (transport_h2g)
- cid = transport_h2g->get_local_cid();
+ cid = vsock_registered_transport_cid(&transport_g2h);
+ if (cid == VMADDR_CID_ANY)
+ cid = vsock_registered_transport_cid(&transport_h2g);
+ if (cid == VMADDR_CID_ANY)
+ cid = vsock_registered_transport_cid(&transport_local);
if (put_user(cid, p) != 0)
retval = -EFAULT;
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-29 10:27:59 +0300