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

STALE3563d

Revision v1 of 8 in this series.

9 messages, 2 authors, 2016-12-07 · open the first message on its own page

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

From: Peng Tao <hidden>
Date: 2016-12-07 10:02:51

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.

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                   | 29 ++++++++++++++++++++++++++
 include/linux/virtio_vsock.h            | 12 +++++++++++
 net/vmw_vsock/af_vsock.c                |  7 +++++++
 net/vmw_vsock/virtio_transport.c        | 36 +++++++++++++++++++++++++++++++++
 net/vmw_vsock/virtio_transport_common.c | 14 ++++++-------
 5 files changed, 91 insertions(+), 7 deletions(-)

-- 
2.7.4

[PATCH 2/4] vhost-vsock: add pkt cancel capability

From: Peng Tao <hidden>
Date: 2016-12-07 10:00:19

To allow canceling all packets of a connection.

Signed-off-by: Peng Tao <redacted>
---
 drivers/vhost/vsock.c        | 29 +++++++++++++++++++++++++++++
 include/linux/virtio_vsock.h |  3 +++
 2 files changed, 32 insertions(+)

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index a504e2e0..0c23b55 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c

@@ -218,6 +218,34 @@ 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;
+	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->vsk != vsk)
+			continue;
+		list_move(&pkt->list, &freeme);
+	}
+	spin_unlock_bh(&vsock->send_pkt_list_lock);
+
+	list_for_each_entry_safe(pkt, n, &freeme, list) {
+		list_del(&pkt->list);
+		virtio_transport_free_pkt(pkt);
+	}
+
+	return 0;
+}
+
 static struct virtio_vsock_pkt *
 vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
 		      unsigned int out, unsigned int in)

@@ -698,6 +726,7 @@ static struct virtio_transport vhost_transport = {
 	},
 
 	.send_pkt = vhost_transport_send_pkt,
+	.cancel_pkt = vhost_transport_cancel_pkt,
 };
 
 static int __init vhost_vsock_init(void)

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 6dd3242..b92e88d 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h

@@ -72,6 +72,9 @@ struct virtio_transport {
 
 	/* Takes ownership of the packet */
 	int (*send_pkt)(struct virtio_vsock_pkt *pkt);
+
+	/* Cancel packets belonging the same vsock */
+	int (*cancel_pkt)(struct vsock_sock *vsk);
 };
 
 ssize_t

-- 
2.7.4

[PATCH 1/4] vsock: track pkt owner vsock

From: Peng Tao <hidden>
Date: 2016-12-07 10:02:51

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..6dd3242 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;
+	struct vsock_sock *vsk;
 	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..cc1eeb5 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->vsk		= 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

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

From: Peng Tao <hidden>
Date: 2016-12-07 10:02:51

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.

Signed-off-by: Peng Tao <redacted>
---
 include/linux/virtio_vsock.h            | 7 +++++++
 net/vmw_vsock/af_vsock.c                | 7 +++++++
 net/vmw_vsock/virtio_transport_common.c | 7 -------
 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index b92e88d..ff6850a 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h

@@ -156,4 +156,11 @@ void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vs
 u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted);
 void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit);
 
+static inline const struct virtio_transport *virtio_transport_get_ops(void)
+{
+	const struct vsock_transport *t = vsock_core_get_transport();
+
+	return container_of(t, struct virtio_transport, transport);
+}
+
 #endif /* _LINUX_VIRTIO_VSOCK_H */

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 8a398b3..ebb50d6 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c

@@ -104,6 +104,7 @@
 #include <linux/unistd.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
+#include <linux/virtio_vsock.h>
 #include <net/sock.h>
 #include <net/af_vsock.h>

@@ -1105,6 +1106,7 @@ 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 +1117,11 @@ 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)
+		virtio_transport_get_ops()->cancel_pkt(vsk);
 
 	sock_put(sk);
 }

@@ -1223,11 +1228,13 @@ 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;
+			virtio_transport_get_ops()->cancel_pkt(vsk);
 			goto out_wait;
 		} else if (timeout == 0) {
 			err = -ETIMEDOUT;
 			sk->sk_state = SS_UNCONNECTED;
 			sock->state = SS_UNCONNECTED;
+			virtio_transport_get_ops()->cancel_pkt(vsk);
 			goto out_wait;
 		}

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index cc1eeb5..72c5dff 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c

@@ -25,13 +25,6 @@
 /* How long to wait for graceful shutdown of a connection */
 #define VSOCK_CLOSE_TIMEOUT (8 * HZ)
 
-static const struct virtio_transport *virtio_transport_get_ops(void)
-{
-	const struct vsock_transport *t = vsock_core_get_transport();
-
-	return container_of(t, struct virtio_transport, transport);
-}
-
 struct virtio_vsock_pkt *
 virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info,
 			   size_t len,

-- 
2.7.4

[PATCH 3/4] vsock: add pkt cancel capability

From: Peng Tao <hidden>
Date: 2016-12-07 10:02:51

Signed-off-by: Peng Tao <redacted>
---
 net/vmw_vsock/virtio_transport.c | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 936d7ee..f88b6ed 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c

@@ -170,6 +170,41 @@ 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;
+	}
+
+	if (pkt->reply)
+		cnt++;
+
+	spin_lock_bh(&vsock->send_pkt_list_lock);
+	list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) {
+		if (pkt->vsk != 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);
+	}
+	atomic_sub(cnt, &vsock->queued_replies);
+
+	return 0;
+}
+
 static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
 {
 	int buf_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE;

@@ -453,6 +488,7 @@ static struct virtio_transport virtio_transport = {
 	},
 
 	.send_pkt = virtio_transport_send_pkt,
+	.cancel_pkt = virtio_transport_cancel_pkt,
 };
 
 static int virtio_vsock_probe(struct virtio_device *vdev)

-- 
2.7.4

Re: [PATCH 3/4] vsock: add pkt cancel capability

From: Stefan Hajnoczi <hidden>
Date: 2016-12-07 13:22:06

On Wed, Dec 07, 2016 at 06:00:20PM +0800, Peng Tao wrote:

quoted hunk

Signed-off-by: Peng Tao <redacted>
---
 net/vmw_vsock/virtio_transport.c | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 936d7ee..f88b6ed 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c

@@ -170,6 +170,41 @@ 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;
+	}
+
+	if (pkt->reply)

pkt is uninitialized.  I guess this if statement should be deleted, you
already take care of counting reply packets below.

+		cnt++;
+
+	spin_lock_bh(&vsock->send_pkt_list_lock);
+	list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) {
+		if (pkt->vsk != 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);
+	}
+	atomic_sub(cnt, &vsock->queued_replies);

If we stopped rx because there were too many replies in flight then we
might be able to resume rx now:

/* Do we now have resources to resume rx processing? */
if (old_val >= virtqueue_get_vring_size(rx_vq) &&
    new_val < virtqueue_get_vring_size(rx_vq))
	queue_work(virtio_vsock_workqueue, &vsock->rx_work);

Re: [PATCH 2/4] vhost-vsock: add pkt cancel capability

From: Stefan Hajnoczi <hidden>
Date: 2016-12-07 13:23:36

On Wed, Dec 07, 2016 at 06:00:19PM +0800, Peng Tao wrote:

quoted hunk

To allow canceling all packets of a connection.

Signed-off-by: Peng Tao <redacted>
---
 drivers/vhost/vsock.c        | 29 +++++++++++++++++++++++++++++
 include/linux/virtio_vsock.h |  3 +++
 2 files changed, 32 insertions(+)

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index a504e2e0..0c23b55 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c

@@ -218,6 +218,34 @@ 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;
+	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->vsk != vsk)
+			continue;
+		list_move(&pkt->list, &freeme);
+	}
+	spin_unlock_bh(&vsock->send_pkt_list_lock);
+
+	list_for_each_entry_safe(pkt, n, &freeme, list) {
+		list_del(&pkt->list);
+		virtio_transport_free_pkt(pkt);
+	}

Please handle queued_replies so we can resume rx if we fall below the
threshold again.

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

From: Stefan Hajnoczi <hidden>
Date: 2016-12-07 13:25:40

On Wed, Dec 07, 2016 at 06:00:21PM +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.

Signed-off-by: Peng Tao <redacted>
---
 include/linux/virtio_vsock.h            | 7 +++++++
 net/vmw_vsock/af_vsock.c                | 7 +++++++
 net/vmw_vsock/virtio_transport_common.c | 7 -------
 3 files changed, 14 insertions(+), 7 deletions(-)

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

Re: [PATCH 3/4] vsock: add pkt cancel capability

From: Peng Tao <hidden>
Date: 2016-12-07 14:47:02

On Wed, Dec 7, 2016 at 9:22 PM, Stefan Hajnoczi [off-list ref] wrote:

On Wed, Dec 07, 2016 at 06:00:20PM +0800, Peng Tao wrote:

quoted

Signed-off-by: Peng Tao <redacted>
---
 net/vmw_vsock/virtio_transport.c | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 936d7ee..f88b6ed 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c

@@ -170,6 +170,41 @@ 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;
+     }
+
+     if (pkt->reply)

pkt is uninitialized.  I guess this if statement should be deleted, you
already take care of counting reply packets below.

ah, sorry! I forgot to delete it after handling cnt below...

quoted

+             cnt++;
+
+     spin_lock_bh(&vsock->send_pkt_list_lock);
+     list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) {
+             if (pkt->vsk != 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);
+     }
+     atomic_sub(cnt, &vsock->queued_replies);

If we stopped rx because there were too many replies in flight then we
might be able to resume rx now:

/* Do we now have resources to resume rx processing? */
if (old_val >= virtqueue_get_vring_size(rx_vq) &&
    new_val < virtqueue_get_vring_size(rx_vq))
        queue_work(virtio_vsock_workqueue, &vsock->rx_work);

Thanks! I totally missed the resume part... I'll send an updated version later.

Cheers,
Tao

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help