@@ -22,9 +22,6 @@
#include "vsock_addr.h"
-/* vsock-specific sock->sk_state constants */
-#define VSOCK_SS_LISTEN 255
-
#define LAST_RESERVED_PORT 1023
#define VSOCK_HASH_SIZE 251
@@ -36,7 +36,7 @@
* not support simultaneous connects (two "client" sockets connecting).
*
* - "Server" sockets are referred to as listener sockets throughout this
- * implementation because they are in the VSOCK_SS_LISTEN state. When a
+ * implementation because they are in the TCP_LISTEN state. When a
* connection request is received (the second kind of socket mentioned above),
* we create a new socket and refer to it as a pending socket. These pending
* sockets are placed on the pending connection list of the listener socket.
@@ -82,6 +82,15 @@
* argument, we must ensure the reference count is increased to ensure the
* socket isn't freed before the function is run; the deferred function will
* then drop the reference.
+ *
+ * - sk->sk_state uses the TCP state constants because they are widely used by
+ * other address families and exposed to userspace tools like ss(8):
+ *
+ * TCP_CLOSE - unconnected
+ * TCP_SYN_SENT - connecting
+ * TCP_ESTABLISHED - connected
+ * TCP_CLOSING - disconnecting
+ * TCP_LISTEN - listening
*/
#include <linux/types.h>
@@ -489,7 +498,7 @@ void vsock_pending_work(struct work_struct *work)
if (vsock_in_connected_table(vsk))
vsock_remove_connected(vsk);
- sk->sk_state = SS_FREE;
+ sk->sk_state = TCP_CLOSE;
out:
release_sock(sk);
@@ -629,7 +638,6 @@ struct sock *__vsock_create(struct net *net,
sk->sk_destruct = vsock_sk_destruct;
sk->sk_backlog_rcv = vsock_queue_rcv_skb;
- sk->sk_state = 0;
sock_reset_flag(sk, SOCK_DONE);
INIT_LIST_HEAD(&vsk->bound_table);
@@ -903,7 +911,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock,
/* Listening sockets that have connections in their accept
* queue can be read.
*/
- if (sk->sk_state == VSOCK_SS_LISTEN
+ if (sk->sk_state == TCP_LISTEN
&& !vsock_is_accept_queue_empty(sk))
mask |= POLLIN | POLLRDNORM;
@@ -932,7 +940,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock,
}
/* Connected sockets that can produce data can be written. */
- if (sk->sk_state == SS_CONNECTED) {
+ if (sk->sk_state == TCP_ESTABLISHED) {
if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
bool space_avail_now = false;
int ret = transport->notify_poll_out(
@@ -954,7 +962,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock,
* POLLOUT|POLLWRNORM when peer is closed and nothing to read,
* but local send is not shutdown.
*/
- if (sk->sk_state == SS_UNCONNECTED) {
+ if (sk->sk_state == TCP_CLOSE) {
if (!(sk->sk_shutdown & SEND_SHUTDOWN))
mask |= POLLOUT | POLLWRNORM;
@@ -1124,9 +1132,9 @@ static void vsock_connect_timeout(struct work_struct *work)
sk = sk_vsock(vsk);
lock_sock(sk);
- if (sk->sk_state == SS_CONNECTING &&
+ if (sk->sk_state == TCP_SYN_SENT &&
(sk->sk_shutdown != SHUTDOWN_MASK)) {
- sk->sk_state = SS_UNCONNECTED;
+ sk->sk_state = TCP_CLOSE;
sk->sk_err = ETIMEDOUT;
sk->sk_error_report(sk);
cancel = 1;
@@ -1172,7 +1180,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
err = -EALREADY;
break;
default:
- if ((sk->sk_state == VSOCK_SS_LISTEN) ||
+ if ((sk->sk_state == TCP_LISTEN) ||
vsock_addr_cast(addr, addr_len, &remote_addr) != 0) {
err = -EINVAL;
goto out;
@@ -1195,7 +1203,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
if (err)
goto out;
- sk->sk_state = SS_CONNECTING;
+ sk->sk_state = TCP_SYN_SENT;
err = transport->connect(vsk);
if (err < 0)
@@ -1215,7 +1223,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
timeout = vsk->connect_timeout;
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- while (sk->sk_state != SS_CONNECTED && sk->sk_err == 0) {
+ while (sk->sk_state != TCP_ESTABLISHED && 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
@@ -1238,13 +1246,13 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
if (signal_pending(current)) {
err = sock_intr_errno(timeout);
- sk->sk_state = SS_UNCONNECTED;
+ sk->sk_state = TCP_CLOSE;
sock->state = SS_UNCONNECTED;
vsock_transport_cancel_pkt(vsk);
goto out_wait;
} else if (timeout == 0) {
err = -ETIMEDOUT;
- sk->sk_state = SS_UNCONNECTED;
+ sk->sk_state = TCP_CLOSE;
sock->state = SS_UNCONNECTED;
vsock_transport_cancel_pkt(vsk);
goto out_wait;
@@ -1255,7 +1263,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
if (sk->sk_err) {
err = -sk->sk_err;
- sk->sk_state = SS_UNCONNECTED;
+ sk->sk_state = TCP_CLOSE;
sock->state = SS_UNCONNECTED;
} else {
err = 0;
@@ -1288,7 +1296,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
goto out;
}
- if (listener->sk_state != VSOCK_SS_LISTEN) {
+ if (listener->sk_state != TCP_LISTEN) {
err = -EINVAL;
goto out;
}
@@ -1378,7 +1386,7 @@ static int vsock_listen(struct socket *sock, int backlog)
}
sk->sk_max_ack_backlog = backlog;
- sk->sk_state = VSOCK_SS_LISTEN;
+ sk->sk_state = TCP_LISTEN;
err = 0;
@@ -1558,7 +1566,7 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
/* Callers should not provide a destination with stream sockets. */
if (msg->msg_namelen) {
- err = sk->sk_state == SS_CONNECTED ? -EISCONN : -EOPNOTSUPP;
+ err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
goto out;
}
@@ -1569,7 +1577,7 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
goto out;
}
- if (sk->sk_state != SS_CONNECTED ||
+ if (sk->sk_state != TCP_ESTABLISHED ||
!vsock_addr_bound(&vsk->local_addr)) {
err = -ENOTCONN;
goto out;
@@ -1693,7 +1701,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
lock_sock(sk);
- if (sk->sk_state != SS_CONNECTED) {
+ if (sk->sk_state != TCP_ESTABLISHED) {
/* Recvmsg is supposed to return 0 if a peer performs an
* orderly shutdown. Differentiate between that case and when a
* peer has not connected or a local shutdown occured with the
@@ -414,7 +414,7 @@ static void virtio_vsock_event_fill(struct virtio_vsock *vsock)
static void virtio_vsock_reset_sock(struct sock *sk)
{
lock_sock(sk);
- sk->sk_state = SS_UNCONNECTED;
+ sk->sk_state = TCP_CLOSE;
sk->sk_err = ECONNRESET;
sk->sk_error_report(sk);
release_sock(sk);
@@ -708,7 +708,7 @@ static void virtio_transport_do_close(struct vsock_sock *vsk,
sock_set_flag(sk, SOCK_DONE);
vsk->peer_shutdown = SHUTDOWN_MASK;
if (vsock_stream_has_data(vsk) <= 0)
- sk->sk_state = SS_DISCONNECTING;
+ sk->sk_state = TCP_CLOSING;
sk->sk_state_change(sk);
if (vsk->close_work_scheduled &&
@@ -748,8 +748,8 @@ static bool virtio_transport_close(struct vsock_sock *vsk)
{
struct sock *sk = &vsk->sk;
- if (!(sk->sk_state == SS_CONNECTED ||
- sk->sk_state == SS_DISCONNECTING))
+ if (!(sk->sk_state == TCP_ESTABLISHED ||
+ sk->sk_state == TCP_CLOSING))
return true;
/* Already received SHUTDOWN from peer, reply with RST */
@@ -801,7 +801,7 @@ virtio_transport_recv_connecting(struct sock *sk,
switch (le16_to_cpu(pkt->hdr.op)) {
case VIRTIO_VSOCK_OP_RESPONSE:
- sk->sk_state = SS_CONNECTED;
+ sk->sk_state = TCP_ESTABLISHED;
sk->sk_socket->state = SS_CONNECTED;
vsock_insert_connected(vsk);
sk->sk_state_change(sk);
@@ -821,7 +821,7 @@ virtio_transport_recv_connecting(struct sock *sk,
destroy:
virtio_transport_reset(vsk, pkt);
- sk->sk_state = SS_UNCONNECTED;
+ sk->sk_state = TCP_CLOSE;
sk->sk_err = skerr;
sk->sk_error_report(sk);
return err;
@@ -857,7 +857,7 @@ virtio_transport_recv_connected(struct sock *sk,
vsk->peer_shutdown |= SEND_SHUTDOWN;
if (vsk->peer_shutdown == SHUTDOWN_MASK &&
vsock_stream_has_data(vsk) <= 0)
- sk->sk_state = SS_DISCONNECTING;
+ sk->sk_state = TCP_CLOSING;
if (le32_to_cpu(pkt->hdr.flags))
sk->sk_state_change(sk);
break;
@@ -928,7 +928,7 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt)
lock_sock_nested(child, SINGLE_DEPTH_NESTING);
- child->sk_state = SS_CONNECTED;
+ child->sk_state = TCP_ESTABLISHED;
vchild = vsock_sk(child);
vsock_addr_init(&vchild->local_addr, le64_to_cpu(pkt->hdr.dst_cid),
@@ -1016,18 +1016,18 @@ void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt)
sk->sk_write_space(sk);
switch (sk->sk_state) {
- case VSOCK_SS_LISTEN:
+ case TCP_LISTEN:
virtio_transport_recv_listen(sk, pkt);
virtio_transport_free_pkt(pkt);
break;
- case SS_CONNECTING:
+ case TCP_SYN_SENT:
virtio_transport_recv_connecting(sk, pkt);
virtio_transport_free_pkt(pkt);
break;
- case SS_CONNECTED:
+ case TCP_ESTABLISHED:
virtio_transport_recv_connected(sk, pkt);
break;
- case SS_DISCONNECTING:
+ case TCP_CLOSING:
virtio_transport_recv_disconnecting(sk, pkt);
virtio_transport_free_pkt(pkt);
break;
@@ -743,7 +743,7 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg)
/* The local context ID may be out of date, update it. */
vsk->local_addr.svm_cid = dst.svm_cid;
- if (sk->sk_state == SS_CONNECTED)
+ if (sk->sk_state == TCP_ESTABLISHED)
vmci_trans(vsk)->notify_ops->handle_notify_pkt(
sk, pkt, true, &dst, &src,
&bh_process_pkt);
@@ -801,7 +801,9 @@ static void vmci_transport_handle_detach(struct sock *sk)
* left in our consume queue.
*/
if (vsock_stream_has_data(vsk) <= 0) {
- if (sk->sk_state == SS_CONNECTING) {
+ sk->sk_state = TCP_CLOSE;
+
+ if (sk->sk_state == TCP_SYN_SENT) {
/* The peer may detach from a queue pair while
* we are still in the connecting state, i.e.,
* if the peer VM is killed after attaching to
@@ -810,12 +812,10 @@ static void vmci_transport_handle_detach(struct sock *sk)
* event like a reset.
*/
- sk->sk_state = SS_UNCONNECTED;
sk->sk_err = ECONNRESET;
sk->sk_error_report(sk);
return;
}
- sk->sk_state = SS_UNCONNECTED;
}
sk->sk_state_change(sk);
}
@@ -883,17 +883,17 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work)
vsock_sk(sk)->local_addr.svm_cid = pkt->dg.dst.context;
switch (sk->sk_state) {
- case VSOCK_SS_LISTEN:
+ case TCP_LISTEN:
vmci_transport_recv_listen(sk, pkt);
break;
- case SS_CONNECTING:
+ case TCP_SYN_SENT:
/* Processing of pending connections for servers goes through
* the listening socket, so see vmci_transport_recv_listen()
* for that path.
*/
vmci_transport_recv_connecting_client(sk, pkt);
break;
- case SS_CONNECTED:
+ case TCP_ESTABLISHED:
vmci_transport_recv_connected(sk, pkt);
break;
default:
@@ -942,7 +942,7 @@ static int vmci_transport_recv_listen(struct sock *sk,
vsock_sk(pending)->local_addr.svm_cid = pkt->dg.dst.context;
switch (pending->sk_state) {
- case SS_CONNECTING:
+ case TCP_SYN_SENT:
err = vmci_transport_recv_connecting_server(sk,
pending,
pkt);
@@ -1072,7 +1072,7 @@ static int vmci_transport_recv_listen(struct sock *sk,
vsock_add_pending(sk, pending);
sk->sk_ack_backlog++;
- pending->sk_state = SS_CONNECTING;
+ pending->sk_state = TCP_SYN_SENT;
vmci_trans(vpending)->produce_size =
vmci_trans(vpending)->consume_size = qp_size;
vmci_trans(vpending)->queue_pair_size = qp_size;
@@ -1197,11 +1197,11 @@ vmci_transport_recv_connecting_server(struct sock *listener,
* the socket will be valid until it is removed from the queue.
*
* If we fail sending the attach below, we remove the socket from the
- * connected list and move the socket to SS_UNCONNECTED before
+ * connected list and move the socket to TCP_CLOSE before
* releasing the lock, so a pending slow path processing of an incoming
* packet will not see the socket in the connected state in that case.
*/
- pending->sk_state = SS_CONNECTED;
+ pending->sk_state = TCP_ESTABLISHED;
vsock_insert_connected(vpending);
@@ -1232,7 +1232,7 @@ vmci_transport_recv_connecting_server(struct sock *listener,
destroy:
pending->sk_err = skerr;
- pending->sk_state = SS_UNCONNECTED;
+ pending->sk_state = TCP_CLOSE;
/* As long as we drop our reference, all necessary cleanup will handle
* when the cleanup function drops its reference and our destruct
* implementation is called. Note that since the listen handler will
@@ -1270,7 +1270,7 @@ vmci_transport_recv_connecting_client(struct sock *sk,
* accounting (it can already be found since it's in the bound
* table).
*/
- sk->sk_state = SS_CONNECTED;
+ sk->sk_state = TCP_ESTABLISHED;
sk->sk_socket->state = SS_CONNECTED;
vsock_insert_connected(vsk);
sk->sk_state_change(sk);
@@ -1338,7 +1338,7 @@ vmci_transport_recv_connecting_client(struct sock *sk,
destroy:
vmci_transport_send_reset(sk, pkt);
- sk->sk_state = SS_UNCONNECTED;
+ sk->sk_state = TCP_CLOSE;
sk->sk_err = skerr;
sk->sk_error_report(sk);
return err;
@@ -1526,7 +1526,7 @@ static int vmci_transport_recv_connected(struct sock *sk,
sock_set_flag(sk, SOCK_DONE);
vsk->peer_shutdown = SHUTDOWN_MASK;
if (vsock_stream_has_data(vsk) <= 0)
- sk->sk_state = SS_DISCONNECTING;
+ sk->sk_state = TCP_CLOSING;
sk->sk_state_change(sk);
break;
@@ -1790,7 +1790,7 @@ static int vmci_transport_connect(struct vsock_sock *vsk)
err = vmci_transport_send_conn_request(
sk, vmci_trans(vsk)->queue_pair_size);
if (err < 0) {
- sk->sk_state = SS_UNCONNECTED;
+ sk->sk_state = TCP_CLOSE;
return err;
}
} else {
@@ -1800,7 +1800,7 @@ static int vmci_transport_connect(struct vsock_sock *vsk)
sk, vmci_trans(vsk)->queue_pair_size,
supported_proto_versions);
if (err < 0) {
- sk->sk_state = SS_UNCONNECTED;
+ sk->sk_state = TCP_CLOSE;
return err;
}
@@ -355,7 +355,7 @@ vmci_transport_notify_pkt_poll_in(struct sock *sk,
* queue. Ask for notifications when there is something to
* read.
*/
- if (sk->sk_state == SS_CONNECTED) {
+ if (sk->sk_state == TCP_ESTABLISHED) {
if (!send_waiting_read(sk, 1))
return -1;
@@ -176,7 +176,7 @@ vmci_transport_notify_pkt_poll_in(struct sock *sk,
* queue. Ask for notifications when there is something to
* read.
*/
- if (sk->sk_state == SS_CONNECTED)
+ if (sk->sk_state == TCP_ESTABLISHED)
vsock_block_update_write_window(sk);
*data_ready_now = false;
}
There are two state fields: socket->state and sock->sk_state. The socket->state field uses SS_UNCONNECTED, SS_CONNECTED, etc while the sock->sk_state typically uses values that match TCP state constants (TCP_CLOSE, TCP_ESTABLISHED). AF_VSOCK does not follow this convention and instead uses SS_* constants for both fields. The sk_state field will be exposed to userspace through the vsock_diag interface for ss(8), netstat(8), and other programs. This patch switches sk_state to TCP state constants so that the meaning of this field is consistent with other address families. Not just AF_INET and AF_INET6 use the TCP constants, AF_UNIX and others do too. The following mapping was used to convert the code: SS_FREE -> TCP_CLOSE SS_UNCONNECTED -> TCP_CLOSE SS_CONNECTING -> TCP_SYN_SENT SS_CONNECTED -> TCP_ESTABLISHED SS_DISCONNECTING -> TCP_CLOSING VSOCK_SS_LISTEN -> TCP_LISTEN In __vsock_create() the sk_state initialization was dropped because sock_init_data() already initializes sk_state to TCP_CLOSE. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/net/af_vsock.h | 3 -- net/vmw_vsock/af_vsock.c | 46 ++++++++++++++++------------ net/vmw_vsock/virtio_transport.c | 2 +- net/vmw_vsock/virtio_transport_common.c | 22 ++++++------- net/vmw_vsock/vmci_transport.c | 34 ++++++++++---------- net/vmw_vsock/vmci_transport_notify.c | 2 +- net/vmw_vsock/vmci_transport_notify_qstate.c | 2 +- 7 files changed, 58 insertions(+), 53 deletions(-)