summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-08-06 09:20:13 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2016-08-06 09:20:13 -0400
commit0803e04011c2e107b9611660301edde94d7010cc (patch)
tree75699c1999c71a93dc8194a9cac338412e36d78d /net
parent80fac0f577a35c437219a2786c1804ab8ca1e998 (diff)
parentb226acab2f6aaa45c2af27279b63f622b23a44bd (diff)
downloadop-kernel-dev-0803e04011c2e107b9611660301edde94d7010cc.zip
op-kernel-dev-0803e04011c2e107b9611660301edde94d7010cc.tar.gz
Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost
Pull virtio/vhost updates from Michael Tsirkin: - new vsock device support in host and guest - platform IOMMU support in host and guest, including compatibility quirks for legacy systems. - misc fixes and cleanups. * tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: VSOCK: Use kvfree() vhost: split out vringh Kconfig vhost: detect 32 bit integer wrap around vhost: new device IOTLB API vhost: drop vringh dependency vhost: convert pre sorted vhost memory array to interval tree vhost: introduce vhost memory accessors VSOCK: Add Makefile and Kconfig VSOCK: Introduce vhost_vsock.ko VSOCK: Introduce virtio_transport.ko VSOCK: Introduce virtio_vsock_common.ko VSOCK: defer sock removal to transports VSOCK: transport-specific vsock_transport functions vhost: drop vringh dependency vop: pull in vhost Kconfig virtio: new feature to detect IOMMU device quirk balloon: check the number of available pages in leak balloon vhost: lockless enqueuing vhost: simplify work flushing
Diffstat (limited to 'net')
-rw-r--r--net/vmw_vsock/Kconfig20
-rw-r--r--net/vmw_vsock/Makefile6
-rw-r--r--net/vmw_vsock/af_vsock.c25
-rw-r--r--net/vmw_vsock/virtio_transport.c624
-rw-r--r--net/vmw_vsock/virtio_transport_common.c992
-rw-r--r--net/vmw_vsock/vmci_transport.c2
6 files changed, 1663 insertions, 6 deletions
diff --git a/net/vmw_vsock/Kconfig b/net/vmw_vsock/Kconfig
index 14810ab..8831e7c 100644
--- a/net/vmw_vsock/Kconfig
+++ b/net/vmw_vsock/Kconfig
@@ -26,3 +26,23 @@ config VMWARE_VMCI_VSOCKETS
To compile this driver as a module, choose M here: the module
will be called vmw_vsock_vmci_transport. If unsure, say N.
+
+config VIRTIO_VSOCKETS
+ tristate "virtio transport for Virtual Sockets"
+ depends on VSOCKETS && VIRTIO
+ select VIRTIO_VSOCKETS_COMMON
+ help
+ This module implements a virtio transport for Virtual Sockets.
+
+ Enable this transport if your Virtual Machine host supports Virtual
+ Sockets over virtio.
+
+ To compile this driver as a module, choose M here: the module will be
+ called vmw_vsock_virtio_transport. If unsure, say N.
+
+config VIRTIO_VSOCKETS_COMMON
+ tristate
+ help
+ This option is selected by any driver which needs to access
+ the virtio_vsock. The module will be called
+ vmw_vsock_virtio_transport_common.
diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile
index 2ce52d7..bc27c70 100644
--- a/net/vmw_vsock/Makefile
+++ b/net/vmw_vsock/Makefile
@@ -1,7 +1,13 @@
obj-$(CONFIG_VSOCKETS) += vsock.o
obj-$(CONFIG_VMWARE_VMCI_VSOCKETS) += vmw_vsock_vmci_transport.o
+obj-$(CONFIG_VIRTIO_VSOCKETS) += vmw_vsock_virtio_transport.o
+obj-$(CONFIG_VIRTIO_VSOCKETS_COMMON) += vmw_vsock_virtio_transport_common.o
vsock-y += af_vsock.o vsock_addr.o
vmw_vsock_vmci_transport-y += vmci_transport.o vmci_transport_notify.o \
vmci_transport_notify_qstate.o
+
+vmw_vsock_virtio_transport-y += virtio_transport.o
+
+vmw_vsock_virtio_transport_common-y += virtio_transport_common.o
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index b96ac91..17dbbe6 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -344,6 +344,16 @@ static bool vsock_in_connected_table(struct vsock_sock *vsk)
return ret;
}
+void vsock_remove_sock(struct vsock_sock *vsk)
+{
+ if (vsock_in_bound_table(vsk))
+ vsock_remove_bound(vsk);
+
+ if (vsock_in_connected_table(vsk))
+ vsock_remove_connected(vsk);
+}
+EXPORT_SYMBOL_GPL(vsock_remove_sock);
+
void vsock_for_each_connected_socket(void (*fn)(struct sock *sk))
{
int i;
@@ -660,12 +670,6 @@ static void __vsock_release(struct sock *sk)
vsk = vsock_sk(sk);
pending = NULL; /* Compiler warning. */
- if (vsock_in_bound_table(vsk))
- vsock_remove_bound(vsk);
-
- if (vsock_in_connected_table(vsk))
- vsock_remove_connected(vsk);
-
transport->release(vsk);
lock_sock(sk);
@@ -1995,6 +1999,15 @@ void vsock_core_exit(void)
}
EXPORT_SYMBOL_GPL(vsock_core_exit);
+const struct vsock_transport *vsock_core_get_transport(void)
+{
+ /* vsock_register_mutex not taken since only the transport uses this
+ * function and only while registered.
+ */
+ return transport;
+}
+EXPORT_SYMBOL_GPL(vsock_core_get_transport);
+
MODULE_AUTHOR("VMware, Inc.");
MODULE_DESCRIPTION("VMware Virtual Socket Family");
MODULE_VERSION("1.0.1.0-k");
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
new file mode 100644
index 0000000..699dfab
--- /dev/null
+++ b/net/vmw_vsock/virtio_transport.c
@@ -0,0 +1,624 @@
+/*
+ * virtio transport for vsock
+ *
+ * Copyright (C) 2013-2015 Red Hat, Inc.
+ * Author: Asias He <asias@redhat.com>
+ * Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * Some of the code is take from Gerd Hoffmann <kraxel@redhat.com>'s
+ * early virtio-vsock proof-of-concept bits.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/atomic.h>
+#include <linux/virtio.h>
+#include <linux/virtio_ids.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_vsock.h>
+#include <net/sock.h>
+#include <linux/mutex.h>
+#include <net/af_vsock.h>
+
+static struct workqueue_struct *virtio_vsock_workqueue;
+static struct virtio_vsock *the_virtio_vsock;
+static DEFINE_MUTEX(the_virtio_vsock_mutex); /* protects the_virtio_vsock */
+
+struct virtio_vsock {
+ struct virtio_device *vdev;
+ struct virtqueue *vqs[VSOCK_VQ_MAX];
+
+ /* Virtqueue processing is deferred to a workqueue */
+ struct work_struct tx_work;
+ struct work_struct rx_work;
+ struct work_struct event_work;
+
+ /* The following fields are protected by tx_lock. vqs[VSOCK_VQ_TX]
+ * must be accessed with tx_lock held.
+ */
+ struct mutex tx_lock;
+
+ struct work_struct send_pkt_work;
+ spinlock_t send_pkt_list_lock;
+ struct list_head send_pkt_list;
+
+ atomic_t queued_replies;
+
+ /* The following fields are protected by rx_lock. vqs[VSOCK_VQ_RX]
+ * must be accessed with rx_lock held.
+ */
+ struct mutex rx_lock;
+ int rx_buf_nr;
+ int rx_buf_max_nr;
+
+ /* The following fields are protected by event_lock.
+ * vqs[VSOCK_VQ_EVENT] must be accessed with event_lock held.
+ */
+ struct mutex event_lock;
+ struct virtio_vsock_event event_list[8];
+
+ u32 guest_cid;
+};
+
+static struct virtio_vsock *virtio_vsock_get(void)
+{
+ return the_virtio_vsock;
+}
+
+static u32 virtio_transport_get_local_cid(void)
+{
+ struct virtio_vsock *vsock = virtio_vsock_get();
+
+ return vsock->guest_cid;
+}
+
+static void
+virtio_transport_send_pkt_work(struct work_struct *work)
+{
+ struct virtio_vsock *vsock =
+ container_of(work, struct virtio_vsock, send_pkt_work);
+ struct virtqueue *vq;
+ bool added = false;
+ bool restart_rx = false;
+
+ mutex_lock(&vsock->tx_lock);
+
+ vq = vsock->vqs[VSOCK_VQ_TX];
+
+ /* Avoid unnecessary interrupts while we're processing the ring */
+ virtqueue_disable_cb(vq);
+
+ for (;;) {
+ struct virtio_vsock_pkt *pkt;
+ struct scatterlist hdr, buf, *sgs[2];
+ int ret, in_sg = 0, out_sg = 0;
+ bool reply;
+
+ spin_lock_bh(&vsock->send_pkt_list_lock);
+ if (list_empty(&vsock->send_pkt_list)) {
+ spin_unlock_bh(&vsock->send_pkt_list_lock);
+ virtqueue_enable_cb(vq);
+ break;
+ }
+
+ pkt = list_first_entry(&vsock->send_pkt_list,
+ struct virtio_vsock_pkt, list);
+ list_del_init(&pkt->list);
+ spin_unlock_bh(&vsock->send_pkt_list_lock);
+
+ reply = pkt->reply;
+
+ sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr));
+ sgs[out_sg++] = &hdr;
+ if (pkt->buf) {
+ sg_init_one(&buf, pkt->buf, pkt->len);
+ sgs[out_sg++] = &buf;
+ }
+
+ ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, pkt, GFP_KERNEL);
+ if (ret < 0) {
+ spin_lock_bh(&vsock->send_pkt_list_lock);
+ list_add(&pkt->list, &vsock->send_pkt_list);
+ spin_unlock_bh(&vsock->send_pkt_list_lock);
+
+ if (!virtqueue_enable_cb(vq) && ret == -ENOSPC)
+ continue; /* retry now that we have more space */
+ break;
+ }
+
+ if (reply) {
+ struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX];
+ int val;
+
+ val = atomic_dec_return(&vsock->queued_replies);
+
+ /* Do we now have resources to resume rx processing? */
+ if (val + 1 == virtqueue_get_vring_size(rx_vq))
+ restart_rx = true;
+ }
+
+ added = true;
+ }
+
+ if (added)
+ virtqueue_kick(vq);
+
+ mutex_unlock(&vsock->tx_lock);
+
+ if (restart_rx)
+ queue_work(virtio_vsock_workqueue, &vsock->rx_work);
+}
+
+static int
+virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt)
+{
+ struct virtio_vsock *vsock;
+ int len = pkt->len;
+
+ vsock = virtio_vsock_get();
+ if (!vsock) {
+ virtio_transport_free_pkt(pkt);
+ return -ENODEV;
+ }
+
+ if (pkt->reply)
+ atomic_inc(&vsock->queued_replies);
+
+ spin_lock_bh(&vsock->send_pkt_list_lock);
+ list_add_tail(&pkt->list, &vsock->send_pkt_list);
+ spin_unlock_bh(&vsock->send_pkt_list_lock);
+
+ queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work);
+ return len;
+}
+
+static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
+{
+ int buf_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE;
+ struct virtio_vsock_pkt *pkt;
+ struct scatterlist hdr, buf, *sgs[2];
+ struct virtqueue *vq;
+ int ret;
+
+ vq = vsock->vqs[VSOCK_VQ_RX];
+
+ do {
+ pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
+ if (!pkt)
+ break;
+
+ pkt->buf = kmalloc(buf_len, GFP_KERNEL);
+ if (!pkt->buf) {
+ virtio_transport_free_pkt(pkt);
+ break;
+ }
+
+ pkt->len = buf_len;
+
+ sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr));
+ sgs[0] = &hdr;
+
+ sg_init_one(&buf, pkt->buf, buf_len);
+ sgs[1] = &buf;
+ ret = virtqueue_add_sgs(vq, sgs, 0, 2, pkt, GFP_KERNEL);
+ if (ret) {
+ virtio_transport_free_pkt(pkt);
+ break;
+ }
+ vsock->rx_buf_nr++;
+ } while (vq->num_free);
+ if (vsock->rx_buf_nr > vsock->rx_buf_max_nr)
+ vsock->rx_buf_max_nr = vsock->rx_buf_nr;
+ virtqueue_kick(vq);
+}
+
+static void virtio_transport_tx_work(struct work_struct *work)
+{
+ struct virtio_vsock *vsock =
+ container_of(work, struct virtio_vsock, tx_work);
+ struct virtqueue *vq;
+ bool added = false;
+
+ vq = vsock->vqs[VSOCK_VQ_TX];
+ mutex_lock(&vsock->tx_lock);
+ do {
+ struct virtio_vsock_pkt *pkt;
+ unsigned int len;
+
+ virtqueue_disable_cb(vq);
+ while ((pkt = virtqueue_get_buf(vq, &len)) != NULL) {
+ virtio_transport_free_pkt(pkt);
+ added = true;
+ }
+ } while (!virtqueue_enable_cb(vq));
+ mutex_unlock(&vsock->tx_lock);
+
+ if (added)
+ queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work);
+}
+
+/* Is there space left for replies to rx packets? */
+static bool virtio_transport_more_replies(struct virtio_vsock *vsock)
+{
+ struct virtqueue *vq = vsock->vqs[VSOCK_VQ_RX];
+ int val;
+
+ smp_rmb(); /* paired with atomic_inc() and atomic_dec_return() */
+ val = atomic_read(&vsock->queued_replies);
+
+ return val < virtqueue_get_vring_size(vq);
+}
+
+static void virtio_transport_rx_work(struct work_struct *work)
+{
+ struct virtio_vsock *vsock =
+ container_of(work, struct virtio_vsock, rx_work);
+ struct virtqueue *vq;
+
+ vq = vsock->vqs[VSOCK_VQ_RX];
+
+ mutex_lock(&vsock->rx_lock);
+
+ do {
+ virtqueue_disable_cb(vq);
+ for (;;) {
+ struct virtio_vsock_pkt *pkt;
+ unsigned int len;
+
+ if (!virtio_transport_more_replies(vsock)) {
+ /* Stop rx until the device processes already
+ * pending replies. Leave rx virtqueue
+ * callbacks disabled.
+ */
+ goto out;
+ }
+
+ pkt = virtqueue_get_buf(vq, &len);
+ if (!pkt) {
+ break;
+ }
+
+ vsock->rx_buf_nr--;
+
+ /* Drop short/long packets */
+ if (unlikely(len < sizeof(pkt->hdr) ||
+ len > sizeof(pkt->hdr) + pkt->len)) {
+ virtio_transport_free_pkt(pkt);
+ continue;
+ }
+
+ pkt->len = len - sizeof(pkt->hdr);
+ virtio_transport_recv_pkt(pkt);
+ }
+ } while (!virtqueue_enable_cb(vq));
+
+out:
+ if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2)
+ virtio_vsock_rx_fill(vsock);
+ mutex_unlock(&vsock->rx_lock);
+}
+
+/* event_lock must be held */
+static int virtio_vsock_event_fill_one(struct virtio_vsock *vsock,
+ struct virtio_vsock_event *event)
+{
+ struct scatterlist sg;
+ struct virtqueue *vq;
+
+ vq = vsock->vqs[VSOCK_VQ_EVENT];
+
+ sg_init_one(&sg, event, sizeof(*event));
+
+ return virtqueue_add_inbuf(vq, &sg, 1, event, GFP_KERNEL);
+}
+
+/* event_lock must be held */
+static void virtio_vsock_event_fill(struct virtio_vsock *vsock)
+{
+ size_t i;
+
+ for (i = 0; i < ARRAY_SIZE(vsock->event_list); i++) {
+ struct virtio_vsock_event *event = &vsock->event_list[i];
+
+ virtio_vsock_event_fill_one(vsock, event);
+ }
+
+ virtqueue_kick(vsock->vqs[VSOCK_VQ_EVENT]);
+}
+
+static void virtio_vsock_reset_sock(struct sock *sk)
+{
+ lock_sock(sk);
+ sk->sk_state = SS_UNCONNECTED;
+ sk->sk_err = ECONNRESET;
+ sk->sk_error_report(sk);
+ release_sock(sk);
+}
+
+static void virtio_vsock_update_guest_cid(struct virtio_vsock *vsock)
+{
+ struct virtio_device *vdev = vsock->vdev;
+ u64 guest_cid;
+
+ vdev->config->get(vdev, offsetof(struct virtio_vsock_config, guest_cid),
+ &guest_cid, sizeof(guest_cid));
+ vsock->guest_cid = le64_to_cpu(guest_cid);
+}
+
+/* event_lock must be held */
+static void virtio_vsock_event_handle(struct virtio_vsock *vsock,
+ struct virtio_vsock_event *event)
+{
+ switch (le32_to_cpu(event->id)) {
+ case VIRTIO_VSOCK_EVENT_TRANSPORT_RESET:
+ virtio_vsock_update_guest_cid(vsock);
+ vsock_for_each_connected_socket(virtio_vsock_reset_sock);
+ break;
+ }
+}
+
+static void virtio_transport_event_work(struct work_struct *work)
+{
+ struct virtio_vsock *vsock =
+ container_of(work, struct virtio_vsock, event_work);
+ struct virtqueue *vq;
+
+ vq = vsock->vqs[VSOCK_VQ_EVENT];
+
+ mutex_lock(&vsock->event_lock);
+
+ do {
+ struct virtio_vsock_event *event;
+ unsigned int len;
+
+ virtqueue_disable_cb(vq);
+ while ((event = virtqueue_get_buf(vq, &len)) != NULL) {
+ if (len == sizeof(*event))
+ virtio_vsock_event_handle(vsock, event);
+
+ virtio_vsock_event_fill_one(vsock, event);
+ }
+ } while (!virtqueue_enable_cb(vq));
+
+ virtqueue_kick(vsock->vqs[VSOCK_VQ_EVENT]);
+
+ mutex_unlock(&vsock->event_lock);
+}
+
+static void virtio_vsock_event_done(struct virtqueue *vq)
+{
+ struct virtio_vsock *vsock = vq->vdev->priv;
+
+ if (!vsock)
+ return;
+ queue_work(virtio_vsock_workqueue, &vsock->event_work);
+}
+
+static void virtio_vsock_tx_done(struct virtqueue *vq)
+{
+ struct virtio_vsock *vsock = vq->vdev->priv;
+
+ if (!vsock)
+ return;
+ queue_work(virtio_vsock_workqueue, &vsock->tx_work);
+}
+
+static void virtio_vsock_rx_done(struct virtqueue *vq)
+{
+ struct virtio_vsock *vsock = vq->vdev->priv;
+
+ if (!vsock)
+ return;
+ queue_work(virtio_vsock_workqueue, &vsock->rx_work);
+}
+
+static struct virtio_transport virtio_transport = {
+ .transport = {
+ .get_local_cid = virtio_transport_get_local_cid,
+
+ .init = virtio_transport_do_socket_init,
+ .destruct = virtio_transport_destruct,
+ .release = virtio_transport_release,
+ .connect = virtio_transport_connect,
+ .shutdown = virtio_transport_shutdown,
+
+ .dgram_bind = virtio_transport_dgram_bind,
+ .dgram_dequeue = virtio_transport_dgram_dequeue,
+ .dgram_enqueue = virtio_transport_dgram_enqueue,
+ .dgram_allow = virtio_transport_dgram_allow,
+
+ .stream_dequeue = virtio_transport_stream_dequeue,
+ .stream_enqueue = virtio_transport_stream_enqueue,
+ .stream_has_data = virtio_transport_stream_has_data,
+ .stream_has_space = virtio_transport_stream_has_space,
+ .stream_rcvhiwat = virtio_transport_stream_rcvhiwat,
+ .stream_is_active = virtio_transport_stream_is_active,
+ .stream_allow = virtio_transport_stream_allow,
+
+ .notify_poll_in = virtio_transport_notify_poll_in,
+ .notify_poll_out = virtio_transport_notify_poll_out,
+ .notify_recv_init = virtio_transport_notify_recv_init,
+ .notify_recv_pre_block = virtio_transport_notify_recv_pre_block,
+ .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue,
+ .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue,
+ .notify_send_init = virtio_transport_notify_send_init,
+ .notify_send_pre_block = virtio_transport_notify_send_pre_block,
+ .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue,
+ .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
+
+ .set_buffer_size = virtio_transport_set_buffer_size,
+ .set_min_buffer_size = virtio_transport_set_min_buffer_size,
+ .set_max_buffer_size = virtio_transport_set_max_buffer_size,
+ .get_buffer_size = virtio_transport_get_buffer_size,
+ .get_min_buffer_size = virtio_transport_get_min_buffer_size,
+ .get_max_buffer_size = virtio_transport_get_max_buffer_size,
+ },
+
+ .send_pkt = virtio_transport_send_pkt,
+};
+
+static int virtio_vsock_probe(struct virtio_device *vdev)
+{
+ vq_callback_t *callbacks[] = {
+ virtio_vsock_rx_done,
+ virtio_vsock_tx_done,
+ virtio_vsock_event_done,
+ };
+ static const char * const names[] = {
+ "rx",
+ "tx",
+ "event",
+ };
+ struct virtio_vsock *vsock = NULL;
+ int ret;
+
+ ret = mutex_lock_interruptible(&the_virtio_vsock_mutex);
+ if (ret)
+ return ret;
+
+ /* Only one virtio-vsock device per guest is supported */
+ if (the_virtio_vsock) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ vsock = kzalloc(sizeof(*vsock), GFP_KERNEL);
+ if (!vsock) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ vsock->vdev = vdev;
+
+ ret = vsock->vdev->config->find_vqs(vsock->vdev, VSOCK_VQ_MAX,
+ vsock->vqs, callbacks, names);
+ if (ret < 0)
+ goto out;
+
+ virtio_vsock_update_guest_cid(vsock);
+
+ ret = vsock_core_init(&virtio_transport.transport);
+ if (ret < 0)
+ goto out_vqs;
+
+ vsock->rx_buf_nr = 0;
+ vsock->rx_buf_max_nr = 0;
+ atomic_set(&vsock->queued_replies, 0);
+
+ vdev->priv = vsock;
+ the_virtio_vsock = vsock;
+ mutex_init(&vsock->tx_lock);
+ mutex_init(&vsock->rx_lock);
+ mutex_init(&vsock->event_lock);
+ spin_lock_init(&vsock->send_pkt_list_lock);
+ INIT_LIST_HEAD(&vsock->send_pkt_list);
+ INIT_WORK(&vsock->rx_work, virtio_transport_rx_work);
+ INIT_WORK(&vsock->tx_work, virtio_transport_tx_work);
+ INIT_WORK(&vsock->event_work, virtio_transport_event_work);
+ INIT_WORK(&vsock->send_pkt_work, virtio_transport_send_pkt_work);
+
+ mutex_lock(&vsock->rx_lock);
+ virtio_vsock_rx_fill(vsock);
+ mutex_unlock(&vsock->rx_lock);
+
+ mutex_lock(&vsock->event_lock);
+ virtio_vsock_event_fill(vsock);
+ mutex_unlock(&vsock->event_lock);
+
+ mutex_unlock(&the_virtio_vsock_mutex);
+ return 0;
+
+out_vqs:
+ vsock->vdev->config->del_vqs(vsock->vdev);
+out:
+ kfree(vsock);
+ mutex_unlock(&the_virtio_vsock_mutex);
+ return ret;
+}
+
+static void virtio_vsock_remove(struct virtio_device *vdev)
+{
+ struct virtio_vsock *vsock = vdev->priv;
+ struct virtio_vsock_pkt *pkt;
+
+ flush_work(&vsock->rx_work);
+ flush_work(&vsock->tx_work);
+ flush_work(&vsock->event_work);
+ flush_work(&vsock->send_pkt_work);
+
+ vdev->config->reset(vdev);
+
+ mutex_lock(&vsock->rx_lock);
+ while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_RX])))
+ virtio_transport_free_pkt(pkt);
+ mutex_unlock(&vsock->rx_lock);
+
+ mutex_lock(&vsock->tx_lock);
+ while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_TX])))
+ virtio_transport_free_pkt(pkt);
+ mutex_unlock(&vsock->tx_lock);
+
+ spin_lock_bh(&vsock->send_pkt_list_lock);
+ while (!list_empty(&vsock->send_pkt_list)) {
+ pkt = list_first_entry(&vsock->send_pkt_list,
+ struct virtio_vsock_pkt, list);
+ list_del(&pkt->list);
+ virtio_transport_free_pkt(pkt);
+ }
+ spin_unlock_bh(&vsock->send_pkt_list_lock);
+
+ mutex_lock(&the_virtio_vsock_mutex);
+ the_virtio_vsock = NULL;
+ vsock_core_exit();
+ mutex_unlock(&the_virtio_vsock_mutex);
+
+ vdev->config->del_vqs(vdev);
+
+ kfree(vsock);
+}
+
+static struct virtio_device_id id_table[] = {
+ { VIRTIO_ID_VSOCK, VIRTIO_DEV_ANY_ID },
+ { 0 },
+};
+
+static unsigned int features[] = {
+};
+
+static struct virtio_driver virtio_vsock_driver = {
+ .feature_table = features,
+ .feature_table_size = ARRAY_SIZE(features),
+ .driver.name = KBUILD_MODNAME,
+ .driver.owner = THIS_MODULE,
+ .id_table = id_table,
+ .probe = virtio_vsock_probe,
+ .remove = virtio_vsock_remove,
+};
+
+static int __init virtio_vsock_init(void)
+{
+ int ret;
+
+ virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0);
+ if (!virtio_vsock_workqueue)
+ return -ENOMEM;
+ ret = register_virtio_driver(&virtio_vsock_driver);
+ if (ret)
+ destroy_workqueue(virtio_vsock_workqueue);
+ return ret;
+}
+
+static void __exit virtio_vsock_exit(void)
+{
+ unregister_virtio_driver(&virtio_vsock_driver);
+ destroy_workqueue(virtio_vsock_workqueue);
+}
+
+module_init(virtio_vsock_init);
+module_exit(virtio_vsock_exit);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Asias He");
+MODULE_DESCRIPTION("virtio transport for vsock");
+MODULE_DEVICE_TABLE(virtio, id_table);
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
new file mode 100644
index 0000000..a53b3a1
--- /dev/null
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -0,0 +1,992 @@
+/*
+ * common code for virtio vsock
+ *
+ * Copyright (C) 2013-2015 Red Hat, Inc.
+ * Author: Asias He <asias@redhat.com>
+ * Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/list.h>
+#include <linux/virtio.h>
+#include <linux/virtio_ids.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_vsock.h>
+
+#include <net/sock.h>
+#include <net/af_vsock.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/vsock_virtio_transport_common.h>
+
+/* 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,
+ u32 src_cid,
+ u32 src_port,
+ u32 dst_cid,
+ u32 dst_port)
+{
+ struct virtio_vsock_pkt *pkt;
+ int err;
+
+ pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
+ if (!pkt)
+ return NULL;
+
+ pkt->hdr.type = cpu_to_le16(info->type);
+ pkt->hdr.op = cpu_to_le16(info->op);
+ pkt->hdr.src_cid = cpu_to_le64(src_cid);
+ pkt->hdr.dst_cid = cpu_to_le64(dst_cid);
+ pkt->hdr.src_port = cpu_to_le32(src_port);
+ pkt->hdr.dst_port = cpu_to_le32(dst_port);
+ pkt->hdr.flags = cpu_to_le32(info->flags);
+ pkt->len = len;
+ pkt->hdr.len = cpu_to_le32(len);
+ pkt->reply = info->reply;
+
+ if (info->msg && len > 0) {
+ pkt->buf = kmalloc(len, GFP_KERNEL);
+ if (!pkt->buf)
+ goto out_pkt;
+ err = memcpy_from_msg(pkt->buf, info->msg, len);
+ if (err)
+ goto out;
+ }
+
+ trace_virtio_transport_alloc_pkt(src_cid, src_port,
+ dst_cid, dst_port,
+ len,
+ info->type,
+ info->op,
+ info->flags);
+
+ return pkt;
+
+out:
+ kfree(pkt->buf);
+out_pkt:
+ kfree(pkt);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_alloc_pkt);
+
+static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
+ struct virtio_vsock_pkt_info *info)
+{
+ u32 src_cid, src_port, dst_cid, dst_port;
+ struct virtio_vsock_sock *vvs;
+ struct virtio_vsock_pkt *pkt;
+ u32 pkt_len = info->pkt_len;
+
+ src_cid = vm_sockets_get_local_cid();
+ src_port = vsk->local_addr.svm_port;
+ if (!info->remote_cid) {
+ dst_cid = vsk->remote_addr.svm_cid;
+ dst_port = vsk->remote_addr.svm_port;
+ } else {
+ dst_cid = info->remote_cid;
+ dst_port = info->remote_port;
+ }
+
+ vvs = vsk->trans;
+
+ /* we can send less than pkt_len bytes */
+ if (pkt_len > VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE)
+ pkt_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE;
+
+ /* virtio_transport_get_credit might return less than pkt_len credit */
+ pkt_len = virtio_transport_get_credit(vvs, pkt_len);
+
+ /* Do not send zero length OP_RW pkt */
+ if (pkt_len == 0 && info->op == VIRTIO_VSOCK_OP_RW)
+ return pkt_len;
+
+ pkt = virtio_transport_alloc_pkt(info, pkt_len,
+ src_cid, src_port,
+ dst_cid, dst_port);
+ if (!pkt) {
+ virtio_transport_put_credit(vvs, pkt_len);
+ return -ENOMEM;
+ }
+
+ virtio_transport_inc_tx_pkt(vvs, pkt);
+
+ return virtio_transport_get_ops()->send_pkt(pkt);
+}
+
+static void virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs,
+ struct virtio_vsock_pkt *pkt)
+{
+ vvs->rx_bytes += pkt->len;
+}
+
+static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs,
+ struct virtio_vsock_pkt *pkt)
+{
+ vvs->rx_bytes -= pkt->len;
+ vvs->fwd_cnt += pkt->len;
+}
+
+void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt)
+{
+ spin_lock_bh(&vvs->tx_lock);
+ pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt);
+ pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc);
+ spin_unlock_bh(&vvs->tx_lock);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt);
+
+u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit)
+{
+ u32 ret;
+
+ spin_lock_bh(&vvs->tx_lock);
+ ret = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
+ if (ret > credit)
+ ret = credit;
+ vvs->tx_cnt += ret;
+ spin_unlock_bh(&vvs->tx_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_get_credit);
+
+void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit)
+{
+ spin_lock_bh(&vvs->tx_lock);
+ vvs->tx_cnt -= credit;
+ spin_unlock_bh(&vvs->tx_lock);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_put_credit);
+
+static int virtio_transport_send_credit_update(struct vsock_sock *vsk,
+ int type,
+ struct virtio_vsock_hdr *hdr)
+{
+ struct virtio_vsock_pkt_info info = {
+ .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE,
+ .type = type,
+ };
+
+ return virtio_transport_send_pkt_info(vsk, &info);
+}
+
+static ssize_t
+virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
+ struct msghdr *msg,
+ size_t len)
+{
+ struct virtio_vsock_sock *vvs = vsk->trans;
+ struct virtio_vsock_pkt *pkt;
+ size_t bytes, total = 0;
+ int err = -EFAULT;
+
+ spin_lock_bh(&vvs->rx_lock);
+ while (total < len && !list_empty(&vvs->rx_queue)) {
+ pkt = list_first_entry(&vvs->rx_queue,
+ struct virtio_vsock_pkt, list);
+
+ bytes = len - total;
+ if (bytes > pkt->len - pkt->off)
+ bytes = pkt->len - pkt->off;
+
+ /* sk_lock is held by caller so no one else can dequeue.
+ * Unlock rx_lock since memcpy_to_msg() may sleep.
+ */
+ spin_unlock_bh(&vvs->rx_lock);
+
+ err = memcpy_to_msg(msg, pkt->buf + pkt->off, bytes);
+ if (err)
+ goto out;
+
+ spin_lock_bh(&vvs->rx_lock);
+
+ total += bytes;
+ pkt->off += bytes;
+ if (pkt->off == pkt->len) {
+ virtio_transport_dec_rx_pkt(vvs, pkt);
+ list_del(&pkt->list);
+ virtio_transport_free_pkt(pkt);
+ }
+ }
+ spin_unlock_bh(&vvs->rx_lock);
+
+ /* Send a credit pkt to peer */
+ virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM,
+ NULL);
+
+ return total;
+
+out:
+ if (total)
+ err = total;
+ return err;
+}
+
+ssize_t
+virtio_transport_stream_dequeue(struct vsock_sock *vsk,
+ struct msghdr *msg,
+ size_t len, int flags)
+{
+ if (flags & MSG_PEEK)
+ return -EOPNOTSUPP;
+
+ return virtio_transport_stream_do_dequeue(vsk, msg, len);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue);
+
+int
+virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
+ struct msghdr *msg,
+ size_t len, int flags)
+{
+ return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_dgram_dequeue);
+
+s64 virtio_transport_stream_has_data(struct vsock_sock *vsk)
+{
+ struct virtio_vsock_sock *vvs = vsk->trans;
+ s64 bytes;
+
+ spin_lock_bh(&vvs->rx_lock);
+ bytes = vvs->rx_bytes;
+ spin_unlock_bh(&vvs->rx_lock);
+
+ return bytes;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_stream_has_data);
+
+static s64 virtio_transport_has_space(struct vsock_sock *vsk)
+{
+ struct virtio_vsock_sock *vvs = vsk->trans;
+ s64 bytes;
+
+ bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
+ if (bytes < 0)
+ bytes = 0;
+
+ return bytes;
+}
+
+s64 virtio_transport_stream_has_space(struct vsock_sock *vsk)
+{
+ struct virtio_vsock_sock *vvs = vsk->trans;
+ s64 bytes;
+
+ spin_lock_bh(&vvs->tx_lock);
+ bytes = virtio_transport_has_space(vsk);
+ spin_unlock_bh(&vvs->tx_lock);
+
+ return bytes;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_stream_has_space);
+
+int virtio_transport_do_socket_init(struct vsock_sock *vsk,
+ struct vsock_sock *psk)
+{
+ struct virtio_vsock_sock *vvs;
+
+ vvs = kzalloc(sizeof(*vvs), GFP_KERNEL);
+ if (!vvs)
+ return -ENOMEM;
+
+ vsk->trans = vvs;
+ vvs->vsk = vsk;
+ if (psk) {
+ struct virtio_vsock_sock *ptrans = psk->trans;
+
+ vvs->buf_size = ptrans->buf_size;
+ vvs->buf_size_min = ptrans->buf_size_min;
+ vvs->buf_size_max = ptrans->buf_size_max;
+ vvs->peer_buf_alloc = ptrans->peer_buf_alloc;
+ } else {
+ vvs->buf_size = VIRTIO_VSOCK_DEFAULT_BUF_SIZE;
+ vvs->buf_size_min = VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE;
+ vvs->buf_size_max = VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE;
+ }
+
+ vvs->buf_alloc = vvs->buf_size;
+
+ spin_lock_init(&vvs->rx_lock);
+ spin_lock_init(&vvs->tx_lock);
+ INIT_LIST_HEAD(&vvs->rx_queue);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_do_socket_init);
+
+u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk)
+{
+ struct virtio_vsock_sock *vvs = vsk->trans;
+
+ return vvs->buf_size;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_get_buffer_size);
+
+u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk)
+{
+ struct virtio_vsock_sock *vvs = vsk->trans;
+
+ return vvs->buf_size_min;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_get_min_buffer_size);
+
+u64 virtio_transport_get_max_buffer_size(struct vsock_sock *vsk)
+{
+ struct virtio_vsock_sock *vvs = vsk->trans;
+
+ return vvs->buf_size_max;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_get_max_buffer_size);
+
+void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val)
+{
+ struct virtio_vsock_sock *vvs = vsk->trans;
+
+ if (val > VIRTIO_VSOCK_MAX_BUF_SIZE)
+ val = VIRTIO_VSOCK_MAX_BUF_SIZE;
+ if (val < vvs->buf_size_min)
+ vvs->buf_size_min = val;
+ if (val > vvs->buf_size_max)
+ vvs->buf_size_max = val;
+ vvs->buf_size = val;
+ vvs->buf_alloc = val;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_set_buffer_size);
+
+void virtio_transport_set_min_buffer_size(struct vsock_sock *vsk, u64 val)
+{
+ struct virtio_vsock_sock *vvs = vsk->trans;
+
+ if (val > VIRTIO_VSOCK_MAX_BUF_SIZE)
+ val = VIRTIO_VSOCK_MAX_BUF_SIZE;
+ if (val > vvs->buf_size)
+ vvs->buf_size = val;
+ vvs->buf_size_min = val;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_set_min_buffer_size);
+
+void virtio_transport_set_max_buffer_size(struct vsock_sock *vsk, u64 val)
+{
+ struct virtio_vsock_sock *vvs = vsk->trans;
+
+ if (val > VIRTIO_VSOCK_MAX_BUF_SIZE)
+ val = VIRTIO_VSOCK_MAX_BUF_SIZE;
+ if (val < vvs->buf_size)
+ vvs->buf_size = val;
+ vvs->buf_size_max = val;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_set_max_buffer_size);
+
+int
+virtio_transport_notify_poll_in(struct vsock_sock *vsk,
+ size_t target,
+ bool *data_ready_now)
+{
+ if (vsock_stream_has_data(vsk))
+ *data_ready_now = true;
+ else
+ *data_ready_now = false;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_notify_poll_in);
+
+int
+virtio_transport_notify_poll_out(struct vsock_sock *vsk,
+ size_t target,
+ bool *space_avail_now)
+{
+ s64 free_space;
+
+ free_space = vsock_stream_has_space(vsk);
+ if (free_space > 0)
+ *space_avail_now = true;
+ else if (free_space == 0)
+ *space_avail_now = false;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_notify_poll_out);
+
+int virtio_transport_notify_recv_init(struct vsock_sock *vsk,
+ size_t target, struct vsock_transport_recv_notify_data *data)
+{
+ return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_init);
+
+int virtio_transport_notify_recv_pre_block(struct vsock_sock *vsk,
+ size_t target, struct vsock_transport_recv_notify_data *data)
+{
+ return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_pre_block);
+
+int virtio_transport_notify_recv_pre_dequeue(struct vsock_sock *vsk,
+ size_t target, struct vsock_transport_recv_notify_data *data)
+{
+ return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_pre_dequeue);
+
+int virtio_transport_notify_recv_post_dequeue(struct vsock_sock *vsk,
+ size_t target, ssize_t copied, bool data_read,
+ struct vsock_transport_recv_notify_data *data)
+{
+ return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_post_dequeue);
+
+int virtio_transport_notify_send_init(struct vsock_sock *vsk,
+ struct vsock_transport_send_notify_data *data)
+{
+ return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_notify_send_init);
+
+int virtio_transport_notify_send_pre_block(struct vsock_sock *vsk,
+ struct vsock_transport_send_notify_data *data)
+{
+ return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_notify_send_pre_block);
+
+int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk,
+ struct vsock_transport_send_notify_data *data)
+{
+ return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_notify_send_pre_enqueue);
+
+int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk,
+ ssize_t written, struct vsock_transport_send_notify_data *data)
+{
+ return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_notify_send_post_enqueue);
+
+u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk)
+{
+ struct virtio_vsock_sock *vvs = vsk->trans;
+
+ return vvs->buf_size;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_stream_rcvhiwat);
+
+bool virtio_transport_stream_is_active(struct vsock_sock *vsk)
+{
+ return true;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_stream_is_active);
+
+bool virtio_transport_stream_allow(u32 cid, u32 port)
+{
+ return true;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_stream_allow);
+
+int virtio_transport_dgram_bind(struct vsock_sock *vsk,
+ struct sockaddr_vm *addr)
+{
+ return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_dgram_bind);
+
+bool virtio_transport_dgram_allow(u32 cid, u32 port)
+{
+ return false;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_dgram_allow);
+
+int virtio_transport_connect(struct vsock_sock *vsk)
+{
+ struct virtio_vsock_pkt_info info = {
+ .op = VIRTIO_VSOCK_OP_REQUEST,
+ .type = VIRTIO_VSOCK_TYPE_STREAM,
+ };
+
+ return virtio_transport_send_pkt_info(vsk, &info);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_connect);
+
+int virtio_transport_shutdown(struct vsock_sock *vsk, int mode)
+{
+ struct virtio_vsock_pkt_info info = {
+ .op = VIRTIO_VSOCK_OP_SHUTDOWN,
+ .type = VIRTIO_VSOCK_TYPE_STREAM,
+ .flags = (mode & RCV_SHUTDOWN ?
+ VIRTIO_VSOCK_SHUTDOWN_RCV : 0) |
+ (mode & SEND_SHUTDOWN ?
+ VIRTIO_VSOCK_SHUTDOWN_SEND : 0),
+ };
+
+ return virtio_transport_send_pkt_info(vsk, &info);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_shutdown);
+
+int
+virtio_transport_dgram_enqueue(struct vsock_sock *vsk,
+ struct sockaddr_vm *remote_addr,
+ struct msghdr *msg,
+ size_t dgram_len)
+{
+ return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_dgram_enqueue);
+
+ssize_t
+virtio_transport_stream_enqueue(struct vsock_sock *vsk,
+ struct msghdr *msg,
+ size_t len)
+{
+ struct virtio_vsock_pkt_info info = {
+ .op = VIRTIO_VSOCK_OP_RW,
+ .type = VIRTIO_VSOCK_TYPE_STREAM,
+ .msg = msg,
+ .pkt_len = len,
+ };
+
+ return virtio_transport_send_pkt_info(vsk, &info);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_stream_enqueue);
+
+void virtio_transport_destruct(struct vsock_sock *vsk)
+{
+ struct virtio_vsock_sock *vvs = vsk->trans;
+
+ kfree(vvs);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_destruct);
+
+static int virtio_transport_reset(struct vsock_sock *vsk,
+ struct virtio_vsock_pkt *pkt)
+{
+ struct virtio_vsock_pkt_info info = {
+ .op = VIRTIO_VSOCK_OP_RST,
+ .type = VIRTIO_VSOCK_TYPE_STREAM,
+ .reply = !!pkt,
+ };
+
+ /* Send RST only if the original pkt is not a RST pkt */
+ if (pkt && le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
+ return 0;
+
+ return virtio_transport_send_pkt_info(vsk, &info);
+}
+
+/* Normally packets are associated with a socket. There may be no socket if an
+ * attempt was made to connect to a socket that does not exist.
+ */
+static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt)
+{
+ struct virtio_vsock_pkt_info info = {
+ .op = VIRTIO_VSOCK_OP_RST,
+ .type = le16_to_cpu(pkt->hdr.type),
+ .reply = true,
+ };
+
+ /* Send RST only if the original pkt is not a RST pkt */
+ if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
+ return 0;
+
+ pkt = virtio_transport_alloc_pkt(&info, 0,
+ le32_to_cpu(pkt->hdr.dst_cid),
+ le32_to_cpu(pkt->hdr.dst_port),
+ le32_to_cpu(pkt->hdr.src_cid),
+ le32_to_cpu(pkt->hdr.src_port));
+ if (!pkt)
+ return -ENOMEM;
+
+ return virtio_transport_get_ops()->send_pkt(pkt);
+}
+
+static void virtio_transport_wait_close(struct sock *sk, long timeout)
+{
+ if (timeout) {
+ DEFINE_WAIT(wait);
+
+ do {
+ prepare_to_wait(sk_sleep(sk), &wait,
+ TASK_INTERRUPTIBLE);
+ if (sk_wait_event(sk, &timeout,
+ sock_flag(sk, SOCK_DONE)))
+ break;
+ } while (!signal_pending(current) && timeout);
+
+ finish_wait(sk_sleep(sk), &wait);
+ }
+}
+
+static void virtio_transport_do_close(struct vsock_sock *vsk,
+ bool cancel_timeout)
+{
+ struct sock *sk = sk_vsock(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_change(sk);
+
+ if (vsk->close_work_scheduled &&
+ (!cancel_timeout || cancel_delayed_work(&vsk->close_work))) {
+ vsk->close_work_scheduled = false;
+
+ vsock_remove_sock(vsk);
+
+ /* Release refcnt obtained when we scheduled the timeout */
+ sock_put(sk);
+ }
+}
+
+static void virtio_transport_close_timeout(struct work_struct *work)
+{
+ struct vsock_sock *vsk =
+ container_of(work, struct vsock_sock, close_work.work);
+ struct sock *sk = sk_vsock(vsk);
+
+ sock_hold(sk);
+ lock_sock(sk);
+
+ if (!sock_flag(sk, SOCK_DONE)) {
+ (void)virtio_transport_reset(vsk, NULL);
+
+ virtio_transport_do_close(vsk, false);
+ }
+
+ vsk->close_work_scheduled = false;
+
+ release_sock(sk);
+ sock_put(sk);
+}
+
+/* User context, vsk->sk is locked */
+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))
+ return true;
+
+ /* Already received SHUTDOWN from peer, reply with RST */
+ if ((vsk->peer_shutdown & SHUTDOWN_MASK) == SHUTDOWN_MASK) {
+ (void)virtio_transport_reset(vsk, NULL);
+ return true;
+ }
+
+ 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 (sock_flag(sk, SOCK_DONE)) {
+ return true;
+ }
+
+ sock_hold(sk);
+ INIT_DELAYED_WORK(&vsk->close_work,
+ virtio_transport_close_timeout);
+ vsk->close_work_scheduled = true;
+ schedule_delayed_work(&vsk->close_work, VSOCK_CLOSE_TIMEOUT);
+ return false;
+}
+
+void virtio_transport_release(struct vsock_sock *vsk)
+{
+ struct sock *sk = &vsk->sk;
+ bool remove_sock = true;
+
+ lock_sock(sk);
+ if (sk->sk_type == SOCK_STREAM)
+ remove_sock = virtio_transport_close(vsk);
+ release_sock(sk);
+
+ if (remove_sock)
+ vsock_remove_sock(vsk);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_release);
+
+static int
+virtio_transport_recv_connecting(struct sock *sk,
+ struct virtio_vsock_pkt *pkt)
+{
+ struct vsock_sock *vsk = vsock_sk(sk);
+ int err;
+ int skerr;
+
+ switch (le16_to_cpu(pkt->hdr.op)) {
+ case VIRTIO_VSOCK_OP_RESPONSE:
+ sk->sk_state = SS_CONNECTED;
+ sk->sk_socket->state = SS_CONNECTED;
+ vsock_insert_connected(vsk);
+ sk->sk_state_change(sk);
+ break;
+ case VIRTIO_VSOCK_OP_INVALID:
+ break;
+ case VIRTIO_VSOCK_OP_RST:
+ skerr = ECONNRESET;
+ err = 0;
+ goto destroy;
+ default:
+ skerr = EPROTO;
+ err = -EINVAL;
+ goto destroy;
+ }
+ return 0;
+
+destroy:
+ virtio_transport_reset(vsk, pkt);
+ sk->sk_state = SS_UNCONNECTED;
+ sk->sk_err = skerr;
+ sk->sk_error_report(sk);
+ return err;
+}
+
+static int
+virtio_transport_recv_connected(struct sock *sk,
+ struct virtio_vsock_pkt *pkt)
+{
+ struct vsock_sock *vsk = vsock_sk(sk);
+ struct virtio_vsock_sock *vvs = vsk->trans;
+ int err = 0;
+
+ switch (le16_to_cpu(pkt->hdr.op)) {
+ case VIRTIO_VSOCK_OP_RW:
+ pkt->len = le32_to_cpu(pkt->hdr.len);
+ pkt->off = 0;
+
+ spin_lock_bh(&vvs->rx_lock);
+ virtio_transport_inc_rx_pkt(vvs, pkt);
+ list_add_tail(&pkt->list, &vvs->rx_queue);
+ spin_unlock_bh(&vvs->rx_lock);
+
+ sk->sk_data_ready(sk);
+ return err;
+ case VIRTIO_VSOCK_OP_CREDIT_UPDATE:
+ sk->sk_write_space(sk);
+ break;
+ case VIRTIO_VSOCK_OP_SHUTDOWN:
+ if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_RCV)
+ vsk->peer_shutdown |= RCV_SHUTDOWN;
+ if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND)
+ vsk->peer_shutdown |= SEND_SHUTDOWN;
+ if (vsk->peer_shutdown == SHUTDOWN_MASK &&
+ vsock_stream_has_data(vsk) <= 0)
+ sk->sk_state = SS_DISCONNECTING;
+ if (le32_to_cpu(pkt->hdr.flags))
+ sk->sk_state_change(sk);
+ break;
+ case VIRTIO_VSOCK_OP_RST:
+ virtio_transport_do_close(vsk, true);
+ break;
+ default:
+ err = -EINVAL;
+ break;
+ }
+
+ virtio_transport_free_pkt(pkt);
+ return err;
+}
+
+static void
+virtio_transport_recv_disconnecting(struct sock *sk,
+ struct virtio_vsock_pkt *pkt)
+{
+ struct vsock_sock *vsk = vsock_sk(sk);
+
+ if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
+ virtio_transport_do_close(vsk, true);
+}
+
+static int
+virtio_transport_send_response(struct vsock_sock *vsk,
+ struct virtio_vsock_pkt *pkt)
+{
+ struct virtio_vsock_pkt_info info = {
+ .op = VIRTIO_VSOCK_OP_RESPONSE,
+ .type = VIRTIO_VSOCK_TYPE_STREAM,
+ .remote_cid = le32_to_cpu(pkt->hdr.src_cid),
+ .remote_port = le32_to_cpu(pkt->hdr.src_port),
+ .reply = true,
+ };
+
+ return virtio_transport_send_pkt_info(vsk, &info);
+}
+
+/* Handle server socket */
+static int
+virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt)
+{
+ struct vsock_sock *vsk = vsock_sk(sk);
+ struct vsock_sock *vchild;
+ struct sock *child;
+
+ if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) {
+ virtio_transport_reset(vsk, pkt);
+ return -EINVAL;
+ }
+
+ if (sk_acceptq_is_full(sk)) {
+ virtio_transport_reset(vsk, pkt);
+ return -ENOMEM;
+ }
+
+ child = __vsock_create(sock_net(sk), NULL, sk, GFP_KERNEL,
+ sk->sk_type, 0);
+ if (!child) {
+ virtio_transport_reset(vsk, pkt);
+ return -ENOMEM;
+ }
+
+ sk->sk_ack_backlog++;
+
+ lock_sock_nested(child, SINGLE_DEPTH_NESTING);
+
+ child->sk_state = SS_CONNECTED;
+
+ vchild = vsock_sk(child);
+ vsock_addr_init(&vchild->local_addr, le32_to_cpu(pkt->hdr.dst_cid),
+ le32_to_cpu(pkt->hdr.dst_port));
+ vsock_addr_init(&vchild->remote_addr, le32_to_cpu(pkt->hdr.src_cid),
+ le32_to_cpu(pkt->hdr.src_port));
+
+ vsock_insert_connected(vchild);
+ vsock_enqueue_accept(sk, child);
+ virtio_transport_send_response(vchild, pkt);
+
+ release_sock(child);
+
+ sk->sk_data_ready(sk);
+ return 0;
+}
+
+static bool virtio_transport_space_update(struct sock *sk,
+ struct virtio_vsock_pkt *pkt)
+{
+ struct vsock_sock *vsk = vsock_sk(sk);
+ struct virtio_vsock_sock *vvs = vsk->trans;
+ bool space_available;
+
+ /* buf_alloc and fwd_cnt is always included in the hdr */
+ spin_lock_bh(&vvs->tx_lock);
+ vvs->peer_buf_alloc = le32_to_cpu(pkt->hdr.buf_alloc);
+ vvs->peer_fwd_cnt = le32_to_cpu(pkt->hdr.fwd_cnt);
+ space_available = virtio_transport_has_space(vsk);
+ spin_unlock_bh(&vvs->tx_lock);
+ return space_available;
+}
+
+/* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex
+ * lock.
+ */
+void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt)
+{
+ struct sockaddr_vm src, dst;
+ struct vsock_sock *vsk;
+ struct sock *sk;
+ bool space_available;
+
+ vsock_addr_init(&src, le32_to_cpu(pkt->hdr.src_cid),
+ le32_to_cpu(pkt->hdr.src_port));
+ vsock_addr_init(&dst, le32_to_cpu(pkt->hdr.dst_cid),
+ le32_to_cpu(pkt->hdr.dst_port));
+
+ trace_virtio_transport_recv_pkt(src.svm_cid, src.svm_port,
+ dst.svm_cid, dst.svm_port,
+ le32_to_cpu(pkt->hdr.len),
+ le16_to_cpu(pkt->hdr.type),
+ le16_to_cpu(pkt->hdr.op),
+ le32_to_cpu(pkt->hdr.flags),
+ le32_to_cpu(pkt->hdr.buf_alloc),
+ le32_to_cpu(pkt->hdr.fwd_cnt));
+
+ if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) {
+ (void)virtio_transport_reset_no_sock(pkt);
+ goto free_pkt;
+ }
+
+ /* The socket must be in connected or bound table
+ * otherwise send reset back
+ */
+ sk = vsock_find_connected_socket(&src, &dst);
+ if (!sk) {
+ sk = vsock_find_bound_socket(&dst);
+ if (!sk) {
+ (void)virtio_transport_reset_no_sock(pkt);
+ goto free_pkt;
+ }
+ }
+
+ vsk = vsock_sk(sk);
+
+ space_available = virtio_transport_space_update(sk, pkt);
+
+ lock_sock(sk);
+
+ /* Update CID in case it has changed after a transport reset event */
+ vsk->local_addr.svm_cid = dst.svm_cid;
+
+ if (space_available)
+ sk->sk_write_space(sk);
+
+ switch (sk->sk_state) {
+ case VSOCK_SS_LISTEN:
+ virtio_transport_recv_listen(sk, pkt);
+ virtio_transport_free_pkt(pkt);
+ break;
+ case SS_CONNECTING:
+ virtio_transport_recv_connecting(sk, pkt);
+ virtio_transport_free_pkt(pkt);
+ break;
+ case SS_CONNECTED:
+ virtio_transport_recv_connected(sk, pkt);
+ break;
+ case SS_DISCONNECTING:
+ virtio_transport_recv_disconnecting(sk, pkt);
+ virtio_transport_free_pkt(pkt);
+ break;
+ default:
+ virtio_transport_free_pkt(pkt);
+ break;
+ }
+ release_sock(sk);
+
+ /* Release refcnt obtained when we fetched this socket out of the
+ * bound or connected list.
+ */
+ sock_put(sk);
+ return;
+
+free_pkt:
+ virtio_transport_free_pkt(pkt);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_recv_pkt);
+
+void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt)
+{
+ kfree(pkt->buf);
+ kfree(pkt);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_free_pkt);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Asias He");
+MODULE_DESCRIPTION("common code for virtio vsock");
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 4120b7a..4be4fbb 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1644,6 +1644,8 @@ static void vmci_transport_destruct(struct vsock_sock *vsk)
static void vmci_transport_release(struct vsock_sock *vsk)
{
+ vsock_remove_sock(vsk);
+
if (!vmci_handle_is_invalid(vmci_trans(vsk)->dg_handle)) {
vmci_datagram_destroy_handle(vmci_trans(vsk)->dg_handle);
vmci_trans(vsk)->dg_handle = VMCI_INVALID_HANDLE;
OpenPOWER on IntegriCloud