summaryrefslogtreecommitdiff
path: root/net/vmw_vsock
diff options
context:
space:
mode:
Diffstat (limited to 'net/vmw_vsock')
-rw-r--r--net/vmw_vsock/af_vsock.c90
-rw-r--r--net/vmw_vsock/virtio_transport_common.c52
-rw-r--r--net/vmw_vsock/vmci_transport.c4
3 files changed, 101 insertions, 45 deletions
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index fc6afbc8d680..1053662725f8 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -407,6 +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;
@@ -464,6 +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;
@@ -479,12 +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
@@ -508,8 +515,16 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
/* 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 ||
@@ -528,12 +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)
@@ -1013,6 +1047,39 @@ out:
return err;
}
+void vsock_linger(struct sock *sk)
+{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ ssize_t (*unsent)(struct vsock_sock *vsk);
+ struct vsock_sock *vsk = vsock_sk(sk);
+ long timeout;
+
+ if (!sock_flag(sk, SOCK_LINGER))
+ return;
+
+ timeout = sk->sk_lingertime;
+ if (!timeout)
+ return;
+
+ /* Transports must implement `unsent_bytes` if they want to support
+ * SOCK_LINGER through `vsock_linger()` since we use it to check when
+ * the socket can be closed.
+ */
+ unsent = vsk->transport->unsent_bytes;
+ if (!unsent)
+ return;
+
+ add_wait_queue(sk_sleep(sk), &wait);
+
+ do {
+ if (sk_wait_event(sk, &timeout, unsent(vsk) == 0, &wait))
+ break;
+ } while (!signal_pending(current) && timeout);
+
+ remove_wait_queue(sk_sleep(sk), &wait);
+}
+EXPORT_SYMBOL_GPL(vsock_linger);
+
static int vsock_shutdown(struct socket *sock, int mode)
{
int err;
@@ -2503,18 +2570,19 @@ 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;
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 7f7de6d88096..1b5d9896edae 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -87,7 +87,7 @@ static int virtio_transport_init_zcopy_skb(struct vsock_sock *vsk,
uarg = msg_zerocopy_realloc(sk_vsock(vsk),
iter->count,
- NULL);
+ NULL, false);
if (!uarg)
return -1;
@@ -107,8 +107,7 @@ static int virtio_transport_fill_skb(struct sk_buff *skb,
{
if (zcopy)
return __zerocopy_sg_from_iter(info->msg, NULL, skb,
- &info->msg->msg_iter,
- len);
+ &info->msg->msg_iter, len, NULL);
return memcpy_from_msg(skb_put(skb, len), info->msg, len);
}
@@ -441,18 +440,20 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs,
u32 len)
{
- if (vvs->rx_bytes + len > vvs->buf_alloc)
+ if (vvs->buf_used + len > vvs->buf_alloc)
return false;
vvs->rx_bytes += len;
+ vvs->buf_used += len;
return true;
}
static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs,
- u32 len)
+ u32 bytes_read, u32 bytes_dequeued)
{
- vvs->rx_bytes -= len;
- vvs->fwd_cnt += len;
+ vvs->rx_bytes -= bytes_read;
+ vvs->buf_used -= bytes_dequeued;
+ vvs->fwd_cnt += bytes_dequeued;
}
void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct sk_buff *skb)
@@ -581,11 +582,11 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
size_t len)
{
struct virtio_vsock_sock *vvs = vsk->trans;
- size_t bytes, total = 0;
struct sk_buff *skb;
u32 fwd_cnt_delta;
bool low_rx_bytes;
int err = -EFAULT;
+ size_t total = 0;
u32 free_space;
spin_lock_bh(&vvs->rx_lock);
@@ -597,6 +598,8 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
}
while (total < len && !skb_queue_empty(&vvs->rx_queue)) {
+ size_t bytes, dequeued = 0;
+
skb = skb_peek(&vvs->rx_queue);
bytes = min_t(size_t, len - total,
@@ -620,12 +623,12 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
VIRTIO_VSOCK_SKB_CB(skb)->offset += bytes;
if (skb->len == VIRTIO_VSOCK_SKB_CB(skb)->offset) {
- u32 pkt_len = le32_to_cpu(virtio_vsock_hdr(skb)->len);
-
- virtio_transport_dec_rx_pkt(vvs, pkt_len);
+ dequeued = le32_to_cpu(virtio_vsock_hdr(skb)->len);
__skb_unlink(skb, &vvs->rx_queue);
consume_skb(skb);
}
+
+ virtio_transport_dec_rx_pkt(vvs, bytes, dequeued);
}
fwd_cnt_delta = vvs->fwd_cnt - vvs->last_fwd_cnt;
@@ -781,7 +784,7 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk,
msg->msg_flags |= MSG_EOR;
}
- virtio_transport_dec_rx_pkt(vvs, pkt_len);
+ virtio_transport_dec_rx_pkt(vvs, pkt_len, pkt_len);
kfree_skb(skb);
}
@@ -1192,23 +1195,6 @@ static void virtio_transport_remove_sock(struct vsock_sock *vsk)
vsock_remove_sock(vsk);
}
-static void virtio_transport_wait_close(struct sock *sk, long timeout)
-{
- if (timeout) {
- DEFINE_WAIT_FUNC(wait, woken_wake_function);
-
- add_wait_queue(sk_sleep(sk), &wait);
-
- do {
- if (sk_wait_event(sk, &timeout,
- sock_flag(sk, SOCK_DONE), &wait))
- break;
- } while (!signal_pending(current) && timeout);
-
- remove_wait_queue(sk_sleep(sk), &wait);
- }
-}
-
static void virtio_transport_cancel_close_work(struct vsock_sock *vsk,
bool cancel_timeout)
{
@@ -1278,8 +1264,8 @@ static bool virtio_transport_close(struct vsock_sock *vsk)
if ((sk->sk_shutdown & SHUTDOWN_MASK) != SHUTDOWN_MASK)
(void)virtio_transport_shutdown(vsk, SHUTDOWN_MASK);
- if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING))
- virtio_transport_wait_close(sk, sk->sk_lingertime);
+ if (!(current->flags & PF_EXITING))
+ vsock_linger(sk);
if (sock_flag(sk, SOCK_DONE)) {
return true;
@@ -1735,6 +1721,7 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto
struct sock *sk = sk_vsock(vsk);
struct virtio_vsock_hdr *hdr;
struct sk_buff *skb;
+ u32 pkt_len;
int off = 0;
int err;
@@ -1752,7 +1739,8 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto
if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM)
vvs->msg_count--;
- virtio_transport_dec_rx_pkt(vvs, le32_to_cpu(hdr->len));
+ pkt_len = le32_to_cpu(hdr->len);
+ virtio_transport_dec_rx_pkt(vvs, pkt_len, pkt_len);
spin_unlock_bh(&vvs->rx_lock);
virtio_transport_send_credit_update(vsk);
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index b370070194fa..7eccd6708d66 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -119,6 +119,8 @@ vmci_transport_packet_init(struct vmci_transport_packet *pkt,
u16 proto,
struct vmci_handle handle)
{
+ memset(pkt, 0, sizeof(*pkt));
+
/* We register the stream control handler as an any cid handle so we
* must always send from a source address of VMADDR_CID_ANY
*/
@@ -131,8 +133,6 @@ vmci_transport_packet_init(struct vmci_transport_packet *pkt,
pkt->type = type;
pkt->src_port = src->svm_port;
pkt->dst_port = dst->svm_port;
- memset(&pkt->proto, 0, sizeof(pkt->proto));
- memset(&pkt->_reserved2, 0, sizeof(pkt->_reserved2));
switch (pkt->type) {
case VMCI_TRANSPORT_PACKET_TYPE_INVALID:
generated by cgit (git 2.34.1) at 2025-07-27 18:07:32 +0000