[PATCH v3 0/4] vsock: cancel connect packets when failing to connect

Currently, if a connect call fails on a signal or timeout (e.g., guest is still
in the process of starting up), we'll just return to caller and leave the connect
packet queued and they are sent even though the connection is considered a failure,
which can confuse applications with unwanted false connect attempt.

The patchset enables vsock (both host and guest) to cancel queued packets when
a connect attempt is considered to fail.

v3 changelog:
  - define cancel_pkt callback in struct vsock_transport rather than struct virtio_transport
  - rename virtio_vsock_pkt->vsk to virtio_vsock_pkt->cancel_token
v2 changelog:
  - fix queued_replies counting and resume tx/rx when necessary


Peng Tao (4):
  vsock: track pkt owner vsock
  vhost-vsock: add pkt cancel capability
  vsock: add pkt cancel capability
  vsock: cancel packets when failing to connect

 drivers/vhost/vsock.c                   | 41 ++++++++++++++++++++++++++++++++
 include/linux/virtio_vsock.h            |  2 ++
 include/net/af_vsock.h                  |  3 +++
 net/vmw_vsock/af_vsock.c                | 14 +++++++++++
 net/vmw_vsock/virtio_transport.c        | 42 +++++++++++++++++++++++++++++++++
 net/vmw_vsock/virtio_transport_common.c |  7 ++++++
 6 files changed, 109 insertions(+)

-- 
2.7.4

So that we can cancel a queued pkt later if necessary.

Signed-off-by: Peng Tao <redacted>
---
 include/linux/virtio_vsock.h            | 2 ++
 net/vmw_vsock/virtio_transport_common.c | 7 +++++++
 2 files changed, 9 insertions(+)

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 9638bfe..193ad3a 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h

@@ -48,6 +48,7 @@ struct virtio_vsock_pkt {
 	struct virtio_vsock_hdr	hdr;
 	struct work_struct work;
 	struct list_head list;
+	void *cancel_token; /* only used for cancellation */
 	void *buf;
 	u32 len;
 	u32 off;

@@ -56,6 +57,7 @@ struct virtio_vsock_pkt {
 
 struct virtio_vsock_pkt_info {
 	u32 remote_cid, remote_port;
+	struct vsock_sock *vsk;
 	struct msghdr *msg;
 	u32 pkt_len;
 	u16 type;

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index a53b3a1..ef94eb8 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c

@@ -57,6 +57,7 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info,
 	pkt->len		= len;
 	pkt->hdr.len		= cpu_to_le32(len);
 	pkt->reply		= info->reply;
+	pkt->cancel_token	= info->vsk;
 
 	if (info->msg && len > 0) {
 		pkt->buf = kmalloc(len, GFP_KERNEL);

@@ -180,6 +181,7 @@ static int virtio_transport_send_credit_update(struct vsock_sock *vsk,
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_CREDIT_UPDATE,
 		.type = type,
+		.vsk = vsk,
 	};
 
 	return virtio_transport_send_pkt_info(vsk, &info);

@@ -519,6 +521,7 @@ int virtio_transport_connect(struct vsock_sock *vsk)
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_REQUEST,
 		.type = VIRTIO_VSOCK_TYPE_STREAM,
+		.vsk = vsk,
 	};
 
 	return virtio_transport_send_pkt_info(vsk, &info);

@@ -534,6 +537,7 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode)
 			  VIRTIO_VSOCK_SHUTDOWN_RCV : 0) |
 			 (mode & SEND_SHUTDOWN ?
 			  VIRTIO_VSOCK_SHUTDOWN_SEND : 0),
+		.vsk = vsk,
 	};
 
 	return virtio_transport_send_pkt_info(vsk, &info);

@@ -560,6 +564,7 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk,
 		.type = VIRTIO_VSOCK_TYPE_STREAM,
 		.msg = msg,
 		.pkt_len = len,
+		.vsk = vsk,
 	};
 
 	return virtio_transport_send_pkt_info(vsk, &info);

@@ -581,6 +586,7 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
 		.op = VIRTIO_VSOCK_OP_RST,
 		.type = VIRTIO_VSOCK_TYPE_STREAM,
 		.reply = !!pkt,
+		.vsk = vsk,
 	};
 
 	/* Send RST only if the original pkt is not a RST pkt */

@@ -826,6 +832,7 @@ virtio_transport_send_response(struct vsock_sock *vsk,
 		.remote_cid = le32_to_cpu(pkt->hdr.src_cid),
 		.remote_port = le32_to_cpu(pkt->hdr.src_port),
 		.reply = true,
+		.vsk = vsk,
 	};
 
 	return virtio_transport_send_pkt_info(vsk, &info);

-- 
2.7.4

To allow canceling all packets of a connection.

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Peng Tao <redacted>
---
 drivers/vhost/vsock.c  | 41 +++++++++++++++++++++++++++++++++++++++++
 include/net/af_vsock.h |  3 +++
 2 files changed, 44 insertions(+)

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index a504e2e0..db64d51 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c

@@ -218,6 +218,46 @@ vhost_transport_send_pkt(struct virtio_vsock_pkt *pkt)
 	return len;
 }
 
+static int
+vhost_transport_cancel_pkt(struct vsock_sock *vsk)
+{
+	struct vhost_vsock *vsock;
+	struct virtio_vsock_pkt *pkt, *n;
+	int cnt = 0;
+	LIST_HEAD(freeme);
+
+	/* Find the vhost_vsock according to guest context id  */
+	vsock = vhost_vsock_get(vsk->remote_addr.svm_cid);
+	if (!vsock)
+		return -ENODEV;
+
+	spin_lock_bh(&vsock->send_pkt_list_lock);
+	list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) {
+		if (pkt->cancel_token != (void *)vsk)
+			continue;
+		list_move(&pkt->list, &freeme);
+	}
+	spin_unlock_bh(&vsock->send_pkt_list_lock);
+
+	list_for_each_entry_safe(pkt, n, &freeme, list) {
+		if (pkt->reply)
+			cnt++;
+		list_del(&pkt->list);
+		virtio_transport_free_pkt(pkt);
+	}
+
+	if (cnt) {
+		struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX];
+		int new_cnt;
+
+		new_cnt = atomic_sub_return(cnt, &vsock->queued_replies);
+		if (new_cnt + cnt >= tx_vq->num && new_cnt < tx_vq->num)
+			vhost_poll_queue(&tx_vq->poll);
+	}
+
+	return 0;
+}
+
 static struct virtio_vsock_pkt *
 vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
 		      unsigned int out, unsigned int in)

@@ -664,6 +704,7 @@ static struct virtio_transport vhost_transport = {
 		.release                  = virtio_transport_release,
 		.connect                  = virtio_transport_connect,
 		.shutdown                 = virtio_transport_shutdown,
+		.cancel_pkt               = vhost_transport_cancel_pkt,
 
 		.dgram_enqueue            = virtio_transport_dgram_enqueue,
 		.dgram_dequeue            = virtio_transport_dgram_dequeue,

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index f275896..ce5f100 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h

@@ -100,6 +100,9 @@ struct vsock_transport {
 	void (*destruct)(struct vsock_sock *);
 	void (*release)(struct vsock_sock *);
 
+	/* Cancel packets belonging the same vsock */
+	int (*cancel_pkt)(struct vsock_sock *vsk);
+
 	/* Connections. */
 	int (*connect)(struct vsock_sock *);
 

-- 
2.7.4

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Peng Tao <redacted>
---
 net/vmw_vsock/virtio_transport.c | 42 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 936d7ee..95c1162 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c

@@ -170,6 +170,47 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt)
 	return len;
 }
 
+static int
+virtio_transport_cancel_pkt(struct vsock_sock *vsk)
+{
+	struct virtio_vsock *vsock;
+	struct virtio_vsock_pkt *pkt, *n;
+	int cnt = 0;
+	LIST_HEAD(freeme);
+
+	vsock = virtio_vsock_get();
+	if (!vsock) {
+		return -ENODEV;
+	}
+
+	spin_lock_bh(&vsock->send_pkt_list_lock);
+	list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) {
+		if (pkt->cancel_token != (void *)vsk)
+			continue;
+		list_move(&pkt->list, &freeme);
+	}
+	spin_unlock_bh(&vsock->send_pkt_list_lock);
+
+	list_for_each_entry_safe(pkt, n, &freeme, list) {
+		if (pkt->reply)
+			cnt++;
+		list_del(&pkt->list);
+		virtio_transport_free_pkt(pkt);
+	}
+
+	if (cnt) {
+		struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX];
+		int new_cnt;
+
+		new_cnt = atomic_sub_return(cnt, &vsock->queued_replies);
+		if (new_cnt + cnt >= virtqueue_get_vring_size(rx_vq) &&
+		    new_cnt < virtqueue_get_vring_size(rx_vq))
+			queue_work(virtio_vsock_workqueue, &vsock->rx_work);
+	}
+
+	return 0;
+}
+
 static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
 {
 	int buf_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE;

@@ -419,6 +460,7 @@ static struct virtio_transport virtio_transport = {
 		.release                  = virtio_transport_release,
 		.connect                  = virtio_transport_connect,
 		.shutdown                 = virtio_transport_shutdown,
+		.cancel_pkt               = virtio_transport_cancel_pkt,
 
 		.dgram_bind               = virtio_transport_dgram_bind,
 		.dgram_dequeue            = virtio_transport_dgram_dequeue,

-- 
2.7.4

Otherwise we'll leave the packets queued until releasing vsock device.
E.g., if guest is slow to start up, resulting ETIMEDOUT on connect, guest
will get the connect requests from failed host sockets.

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Peng Tao <redacted>
---
 net/vmw_vsock/af_vsock.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 8a398b3..c73b03a 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c

@@ -1101,10 +1101,19 @@ static const struct proto_ops vsock_dgram_ops = {
 	.sendpage = sock_no_sendpage,
 };
 
+static int vsock_transport_cancel_pkt(struct vsock_sock *vsk)
+{
+	if (!transport->cancel_pkt)
+		return -EOPNOTSUPP;
+
+	return transport->cancel_pkt(vsk);
+}
+
 static void vsock_connect_timeout(struct work_struct *work)
 {
 	struct sock *sk;
 	struct vsock_sock *vsk;
+	int cancel = 0;
 
 	vsk = container_of(work, struct vsock_sock, dwork.work);
 	sk = sk_vsock(vsk);

@@ -1115,8 +1124,11 @@ static void vsock_connect_timeout(struct work_struct *work)
 		sk->sk_state = SS_UNCONNECTED;
 		sk->sk_err = ETIMEDOUT;
 		sk->sk_error_report(sk);
+		cancel = 1;
 	}
 	release_sock(sk);
+	if (cancel)
+		vsock_transport_cancel_pkt(vsk);
 
 	sock_put(sk);
 }

@@ -1223,11 +1235,13 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 			err = sock_intr_errno(timeout);
 			sk->sk_state = SS_UNCONNECTED;
 			sock->state = SS_UNCONNECTED;
+			vsock_transport_cancel_pkt(vsk);
 			goto out_wait;
 		} else if (timeout == 0) {
 			err = -ETIMEDOUT;
 			sk->sk_state = SS_UNCONNECTED;
 			sock->state = SS_UNCONNECTED;
+			vsock_transport_cancel_pkt(vsk);
 			goto out_wait;
 		}
 

-- 
2.7.4

On Fri, Dec 09, 2016 at 01:12:34AM +0800, Peng Tao wrote:

It's not necessary to cast to void* in C.  All pointers cast to void*
automatically without compiler warnings.  The warnings and explicit
casts are a C++ thing.

On Fri, Dec 09, 2016 at 01:12:35AM +0800, Peng Tao wrote:

The cast is unnecessary here.

On Fri, Dec 09, 2016 at 01:12:36AM +0800, Peng Tao wrote:

Otherwise we'll leave the packets queued until releasing vsock device.
E.g., if guest is slow to start up, resulting ETIMEDOUT on connect, guest
will get the connect requests from failed host sockets.

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

Please do not include Reviewed-by: if the patch has undergone
substantial changes.

I am happy with this latest version:
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

On Fri, Dec 09, 2016 at 01:12:32AM +0800, Peng Tao wrote:

Currently, if a connect call fails on a signal or timeout (e.g., guest is still
in the process of starting up), we'll just return to caller and leave the connect
packet queued and they are sent even though the connection is considered a failure,
which can confuse applications with unwanted false connect attempt.

The patchset enables vsock (both host and guest) to cancel queued packets when
a connect attempt is considered to fail.

v3 changelog:
  - define cancel_pkt callback in struct vsock_transport rather than struct virtio_transport
  - rename virtio_vsock_pkt->vsk to virtio_vsock_pkt->cancel_token
v2 changelog:
  - fix queued_replies counting and resume tx/rx when necessary


Peng Tao (4):
  vsock: track pkt owner vsock
  vhost-vsock: add pkt cancel capability
  vsock: add pkt cancel capability
  vsock: cancel packets when failing to connect

 drivers/vhost/vsock.c                   | 41 ++++++++++++++++++++++++++++++++
 include/linux/virtio_vsock.h            |  2 ++
 include/net/af_vsock.h                  |  3 +++
 net/vmw_vsock/af_vsock.c                | 14 +++++++++++
 net/vmw_vsock/virtio_transport.c        | 42 +++++++++++++++++++++++++++++++++
 net/vmw_vsock/virtio_transport_common.c |  7 ++++++
 6 files changed, 109 insertions(+)

I'm happy although I pointed out two unnecessary (void*) casts.

Please wait for Jorgen to go happy on the af_vsock.c changes before
applying.

On Fri, Dec 9, 2016 at 6:18 PM, Stefan Hajnoczi [off-list ref] wrote:

On Fri, Dec 09, 2016 at 01:12:32AM +0800, Peng Tao wrote:

quoted

Currently, if a connect call fails on a signal or timeout (e.g., guest is still
in the process of starting up), we'll just return to caller and leave the connect
packet queued and they are sent even though the connection is considered a failure,
which can confuse applications with unwanted false connect attempt.

The patchset enables vsock (both host and guest) to cancel queued packets when
a connect attempt is considered to fail.

v3 changelog:
  - define cancel_pkt callback in struct vsock_transport rather than struct virtio_transport
  - rename virtio_vsock_pkt->vsk to virtio_vsock_pkt->cancel_token
v2 changelog:
  - fix queued_replies counting and resume tx/rx when necessary


Peng Tao (4):
  vsock: track pkt owner vsock
  vhost-vsock: add pkt cancel capability
  vsock: add pkt cancel capability
  vsock: cancel packets when failing to connect

 drivers/vhost/vsock.c                   | 41 ++++++++++++++++++++++++++++++++
 include/linux/virtio_vsock.h            |  2 ++
 include/net/af_vsock.h                  |  3 +++
 net/vmw_vsock/af_vsock.c                | 14 +++++++++++
 net/vmw_vsock/virtio_transport.c        | 42 +++++++++++++++++++++++++++++++++
 net/vmw_vsock/virtio_transport_common.c |  7 ++++++
 6 files changed, 109 insertions(+)

I'm happy although I pointed out two unnecessary (void*) casts.

Please wait for Jorgen to go happy on the af_vsock.c changes before
applying.

Thanks for reviewing!

Jorgen, would you please see if the changes to af_vsock.c is OK to you?

Cheers,
Tao

How about “/* Cancel all pending packets sent on vsock. */“ ? 

+	int (*cancel_pkt)(struct vsock_sock *vsk);
+
	/* Connections. */
	int (*connect)(struct vsock_sock *);

-- 
2.7.4

Thanks,
Jørgen
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

This looks fine to me:

Reviewed-by: Jorgen Hansen <redacted>

On Mon, Dec 12, 2016 at 6:37 PM, Jorgen S. Hansen [off-list ref] wrote:

quoted

On Dec 8, 2016, at 6:12 PM, Peng Tao [off-list ref] wrote:

--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h

@@ -100,6 +100,9 @@ struct vsock_transport {
      void (*destruct)(struct vsock_sock *);
      void (*release)(struct vsock_sock *);

+     /* Cancel packets belonging the same vsock */

How about “/* Cancel all pending packets sent on vsock. */“ ?

Sure. I'll update it.

Thanks,
Tao
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization