From: Asias He <asias@xxxxxxxxxx>
This module contains the common code and header files for the following
virtio-vsock and virtio-vhost kernel modules.
Signed-off-by: Asias He <asias@xxxxxxxxxx>
Signed-off-by: Stefan Hajnoczi <stefanha@xxxxxxxxxx>
---
v3:
* Remove unnecessary 3-way handshake, just do REQUEST/RESPONSE instead
of REQUEST/RESPONSE/ACK
* Remove SOCK_DGRAM support and focus on SOCK_STREAM first
* Only allow host->guest connections (same security model as latest
VMware)
v2:
* Fix peer_buf_alloc inheritance on child socket
* Notify other side of SOCK_STREAM disconnect (fixes shutdown
semantics)
* Avoid recursive mutex_lock(tx_lock) for write_space (fixes deadlock)
* Define VIRTIO_VSOCK_TYPE_STREAM/DGRAM hardware interface constants
* Define VIRTIO_VSOCK_SHUTDOWN_RCV/SEND hardware interface constants
---
include/linux/virtio_vsock.h | 203 ++++++++
include/uapi/linux/virtio_ids.h | 1 +
include/uapi/linux/virtio_vsock.h | 87 ++++
net/vmw_vsock/virtio_transport_common.c | 854 ++++++++++++++++++++++++++++++++
4 files changed, 1145 insertions(+)
create mode 100644 include/linux/virtio_vsock.h
create mode 100644 include/uapi/linux/virtio_vsock.h
create mode 100644 net/vmw_vsock/virtio_transport_common.c
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
new file mode 100644
index 0000000..e54eb45
--- /dev/null
+++ b/include/linux/virtio_vsock.h
@@ -0,0 +1,203 @@
+/*
+ * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
+ * anyone can use the definitions to implement compatible drivers/servers:
+ *
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS''
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ * Copyright (C) Red Hat, Inc., 2013-2015
+ * Copyright (C) Asias He <asias@xxxxxxxxxx>, 2013
+ * Copyright (C) Stefan Hajnoczi <stefanha@xxxxxxxxxx>, 2015
+ */
+
+#ifndef _LINUX_VIRTIO_VSOCK_H
+#define _LINUX_VIRTIO_VSOCK_H
+
+#include <uapi/linux/virtio_vsock.h>
+#include <linux/socket.h>
+#include <net/sock.h>
+
+#define VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE 128
+#define VIRTIO_VSOCK_DEFAULT_BUF_SIZE (1024 * 256)
+#define VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE (1024 * 256)
+#define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE (1024 * 4)
+#define VIRTIO_VSOCK_MAX_BUF_SIZE 0xFFFFFFFFUL
+#define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (1024 * 64)
+#define VIRTIO_VSOCK_MAX_TX_BUF_SIZE (1024 * 1024 * 16)
+#define VIRTIO_VSOCK_MAX_DGRAM_SIZE (1024 * 64)
+
+struct vsock_transport_recv_notify_data;
+struct vsock_transport_send_notify_data;
+struct sockaddr_vm;
+struct vsock_sock;
+
+enum {
+ VSOCK_VQ_CTRL = 0,
+ VSOCK_VQ_RX = 1, /* for host to guest data */
+ VSOCK_VQ_TX = 2, /* for guest to host data */
+ VSOCK_VQ_MAX = 3,
+};
+
+/* virtio transport socket state */
+struct virtio_transport {
+ struct virtio_transport_pkt_ops *ops;
+ struct vsock_sock *vsk;
+
+ u32 buf_size;
+ u32 buf_size_min;
+ u32 buf_size_max;
+
+ struct mutex tx_lock;
+ struct mutex rx_lock;
+
+ struct list_head rx_queue;
+ u32 rx_bytes;
+
+ /* Protected by trans->tx_lock */
+ u32 tx_cnt;
+ u32 buf_alloc;
+ u32 peer_fwd_cnt;
+ u32 peer_buf_alloc;
+ /* Protected by trans->rx_lock */
+ u32 fwd_cnt;
+};
+
+struct virtio_vsock_pkt {
+ struct virtio_vsock_hdr hdr;
+ struct virtio_transport *trans;
+ struct work_struct work;
+ struct list_head list;
+ void *buf;
+ u32 len;
+ u32 off;
+};
+
+struct virtio_vsock_pkt_info {
+ u32 remote_cid, remote_port;
+ struct msghdr *msg;
+ u32 pkt_len;
+ u16 type;
+ u16 op;
+ u32 flags;
+};
+
+struct virtio_transport_pkt_ops {
+ int (*send_pkt)(struct vsock_sock *vsk,
+ struct virtio_vsock_pkt_info *info);
+};
+
+void virtio_vsock_dumppkt(const char *func,
+ const struct virtio_vsock_pkt *pkt);
+
+struct sock *
+virtio_transport_get_pending(struct sock *listener,
+ struct virtio_vsock_pkt *pkt);
+struct virtio_vsock_pkt *
+virtio_transport_alloc_pkt(struct vsock_sock *vsk,
+ struct virtio_vsock_pkt_info *info,
+ size_t len,
+ u32 src_cid,
+ u32 src_port,
+ u32 dst_cid,
+ u32 dst_port);
+ssize_t
+virtio_transport_stream_dequeue(struct vsock_sock *vsk,
+ struct msghdr *msg,
+ size_t len,
+ int type);
+int
+virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
+ struct msghdr *msg,
+ size_t len, int flags);
+
+s64 virtio_transport_stream_has_data(struct vsock_sock *vsk);
+s64 virtio_transport_stream_has_space(struct vsock_sock *vsk);
+
+int virtio_transport_do_socket_init(struct vsock_sock *vsk,
+ struct vsock_sock *psk);
+u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk);
+u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk);
+u64 virtio_transport_get_max_buffer_size(struct vsock_sock *vsk);
+void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val);
+void virtio_transport_set_min_buffer_size(struct vsock_sock *vsk, u64 val);
+void virtio_transport_set_max_buffer_size(struct vsock_sock *vs, u64 val);
+int
+virtio_transport_notify_poll_in(struct vsock_sock *vsk,
+ size_t target,
+ bool *data_ready_now);
+int
+virtio_transport_notify_poll_out(struct vsock_sock *vsk,
+ size_t target,
+ bool *space_available_now);
+
+int virtio_transport_notify_recv_init(struct vsock_sock *vsk,
+ size_t target, struct vsock_transport_recv_notify_data *data);
+int virtio_transport_notify_recv_pre_block(struct vsock_sock *vsk,
+ size_t target, struct vsock_transport_recv_notify_data *data);
+int virtio_transport_notify_recv_pre_dequeue(struct vsock_sock *vsk,
+ size_t target, struct vsock_transport_recv_notify_data *data);
+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);
+int virtio_transport_notify_send_init(struct vsock_sock *vsk,
+ struct vsock_transport_send_notify_data *data);
+int virtio_transport_notify_send_pre_block(struct vsock_sock *vsk,
+ struct vsock_transport_send_notify_data *data);
+int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk,
+ struct vsock_transport_send_notify_data *data);
+int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk,
+ ssize_t written, struct vsock_transport_send_notify_data *data);
+
+u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk);
+bool virtio_transport_stream_is_active(struct vsock_sock *vsk);
+bool virtio_transport_stream_allow(u32 cid, u32 port);
+int virtio_transport_dgram_bind(struct vsock_sock *vsk,
+ struct sockaddr_vm *addr);
+bool virtio_transport_dgram_allow(u32 cid, u32 port);
+
+int virtio_transport_connect(struct vsock_sock *vsk);
+
+int virtio_transport_shutdown(struct vsock_sock *vsk, int mode);
+
+void virtio_transport_release(struct vsock_sock *vsk);
+
+ssize_t
+virtio_transport_stream_enqueue(struct vsock_sock *vsk,
+ struct msghdr *msg,
+ size_t len);
+int
+virtio_transport_dgram_enqueue(struct vsock_sock *vsk,
+ struct sockaddr_vm *remote_addr,
+ struct msghdr *msg,
+ size_t len);
+
+void virtio_transport_destruct(struct vsock_sock *vsk);
+
+void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt);
+void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt);
+void virtio_transport_inc_tx_pkt(struct virtio_vsock_pkt *pkt);
+void virtio_transport_dec_tx_pkt(struct virtio_vsock_pkt *pkt);
+u32 virtio_transport_get_credit(struct virtio_transport *trans, u32 wanted);
+void virtio_transport_put_credit(struct virtio_transport *trans, u32 credit);
+#endif /* _LINUX_VIRTIO_VSOCK_H */
diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h
index 77925f5..16dcf5d 100644
--- a/include/uapi/linux/virtio_ids.h
+++ b/include/uapi/linux/virtio_ids.h
@@ -39,6 +39,7 @@
#define VIRTIO_ID_9P 9 /* 9p virtio console */
#define VIRTIO_ID_RPROC_SERIAL 11 /* virtio remoteproc serial link */
#define VIRTIO_ID_CAIF 12 /* Virtio caif */
+#define VIRTIO_ID_VSOCK 13 /* virtio vsock transport */
#define VIRTIO_ID_GPU 16 /* virtio GPU */
#define VIRTIO_ID_INPUT 18 /* virtio input */
diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h
new file mode 100644
index 0000000..ac6483d
--- /dev/null
+++ b/include/uapi/linux/virtio_vsock.h
@@ -0,0 +1,87 @@
+/*
+ * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
+ * anyone can use the definitions to implement compatible drivers/servers:
+ *
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS''
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ * Copyright (C) Red Hat, Inc., 2013-2015
+ * Copyright (C) Asias He <asias@xxxxxxxxxx>, 2013
+ * Copyright (C) Stefan Hajnoczi <stefanha@xxxxxxxxxx>, 2015
+ */
+
+#ifndef _UAPI_LINUX_VIRTIO_VSOCK_H
+#define _UAPI_LINUX_VIRTIO_VOSCK_H
+
+#include <linux/types.h>
+#include <linux/virtio_ids.h>
+#include <linux/virtio_config.h>
+
+struct virtio_vsock_config {
+ __le32 guest_cid;
+ __le32 max_virtqueue_pairs;
+};
+
+struct virtio_vsock_hdr {
+ __le32 src_cid;
+ __le32 src_port;
+ __le32 dst_cid;
+ __le32 dst_port;
+ __le32 len;
+ __le16 type; /* enum virtio_vsock_type */
+ __le16 op; /* enum virtio_vsock_op */
+ __le32 flags;
+ __le32 buf_alloc;
+ __le32 fwd_cnt;
+};
+
+enum virtio_vsock_type {
+ VIRTIO_VSOCK_TYPE_STREAM = 1,
+};
+
+enum virtio_vsock_op {
+ VIRTIO_VSOCK_OP_INVALID = 0,
+
+ /* Connect operations */
+ VIRTIO_VSOCK_OP_REQUEST = 1,
+ VIRTIO_VSOCK_OP_RESPONSE = 2,
+ VIRTIO_VSOCK_OP_RST = 3,
+ VIRTIO_VSOCK_OP_SHUTDOWN = 4,
+
+ /* To send payload */
+ VIRTIO_VSOCK_OP_RW = 5,
+
+ /* Tell the peer our credit info */
+ VIRTIO_VSOCK_OP_CREDIT_UPDATE = 6,
+ /* Request the peer to send the credit info to us */
+ VIRTIO_VSOCK_OP_CREDIT_REQUEST = 7,
+};
+
+/* VIRTIO_VSOCK_OP_SHUTDOWN flags values */
+enum virtio_vsock_shutdown {
+ VIRTIO_VSOCK_SHUTDOWN_RCV = 1,
+ VIRTIO_VSOCK_SHUTDOWN_SEND = 2,
+};
+
+#endif /* _UAPI_LINUX_VIRTIO_VSOCK_H */
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
new file mode 100644
index 0000000..025a323
--- /dev/null
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -0,0 +1,854 @@
+/*
+ * common code for virtio vsock
+ *
+ * Copyright (C) 2013-2015 Red Hat, Inc.
+ * Author: Asias He <asias@xxxxxxxxxx>
+ * Stefan Hajnoczi <stefanha@xxxxxxxxxx>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+#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>
+
+void virtio_vsock_dumppkt(const char *func, const struct virtio_vsock_pkt *pkt)
+{
+ pr_debug("%s: pkt=%p, op=%d, len=%d, %d:%d---%d:%d, len=%d\n",
+ func, pkt,
+ le16_to_cpu(pkt->hdr.op),
+ le32_to_cpu(pkt->hdr.len),
+ le32_to_cpu(pkt->hdr.src_cid),
+ le32_to_cpu(pkt->hdr.src_port),
+ le32_to_cpu(pkt->hdr.dst_cid),
+ le32_to_cpu(pkt->hdr.dst_port),
+ pkt->len);
+}
+EXPORT_SYMBOL_GPL(virtio_vsock_dumppkt);
+
+struct virtio_vsock_pkt *
+virtio_transport_alloc_pkt(struct vsock_sock *vsk,
+ struct virtio_vsock_pkt_info *info,
+ size_t len,
+ u32 src_cid,
+ u32 src_port,
+ u32 dst_cid,
+ u32 dst_port)
+{
+ struct virtio_transport *trans = vsk->trans;
+ struct virtio_vsock_pkt *pkt;
+ int err;
+
+ BUG_ON(!trans);
+
+ 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_le32(src_cid);
+ pkt->hdr.src_port = cpu_to_le32(src_port);
+ pkt->hdr.dst_cid = cpu_to_le32(dst_cid);
+ pkt->hdr.dst_port = cpu_to_le32(dst_port);
+ pkt->hdr.flags = cpu_to_le32(info->flags);
+ pkt->len = len;
+ pkt->trans = trans;
+ pkt->hdr.len = cpu_to_le32(len);
+
+ 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;
+ }
+
+ return pkt;
+
+out:
+ kfree(pkt->buf);
+out_pkt:
+ kfree(pkt);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_alloc_pkt);
+
+struct sock *
+virtio_transport_get_pending(struct sock *listener,
+ struct virtio_vsock_pkt *pkt)
+{
+ struct vsock_sock *vlistener;
+ struct vsock_sock *vpending;
+ struct sockaddr_vm src;
+ struct sockaddr_vm dst;
+ struct sock *pending;
+
+ 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));
+
+ vlistener = vsock_sk(listener);
+ list_for_each_entry(vpending, &vlistener->pending_links,
+ pending_links) {
+ if (vsock_addr_equals_addr(&src, &vpending->remote_addr) &&
+ vsock_addr_equals_addr(&dst, &vpending->local_addr)) {
+ pending = sk_vsock(vpending);
+ sock_hold(pending);
+ return pending;
+ }
+ }
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_get_pending);
+
+static void virtio_transport_inc_rx_pkt(struct virtio_vsock_pkt *pkt)
+{
+ pkt->trans->rx_bytes += pkt->len;
+}
+
+static void virtio_transport_dec_rx_pkt(struct virtio_vsock_pkt *pkt)
+{
+ pkt->trans->rx_bytes -= pkt->len;
+ pkt->trans->fwd_cnt += pkt->len;
+}
+
+void virtio_transport_inc_tx_pkt(struct virtio_vsock_pkt *pkt)
+{
+ mutex_lock(&pkt->trans->tx_lock);
+ pkt->hdr.fwd_cnt = cpu_to_le32(pkt->trans->fwd_cnt);
+ pkt->hdr.buf_alloc = cpu_to_le32(pkt->trans->buf_alloc);
+ mutex_unlock(&pkt->trans->tx_lock);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt);
+
+void virtio_transport_dec_tx_pkt(struct virtio_vsock_pkt *pkt)
+{
+}
+EXPORT_SYMBOL_GPL(virtio_transport_dec_tx_pkt);
+
+u32 virtio_transport_get_credit(struct virtio_transport *trans, u32 credit)
+{
+ u32 ret;
+
+ mutex_lock(&trans->tx_lock);
+ ret = trans->peer_buf_alloc - (trans->tx_cnt - trans->peer_fwd_cnt);
+ if (ret > credit)
+ ret = credit;
+ trans->tx_cnt += ret;
+ mutex_unlock(&trans->tx_lock);
+
+ pr_debug("%s: ret=%d, buf_alloc=%d, peer_buf_alloc=%d,"
+ "tx_cnt=%d, fwd_cnt=%d, peer_fwd_cnt=%d\n", __func__,
+ ret, trans->buf_alloc, trans->peer_buf_alloc,
+ trans->tx_cnt, trans->fwd_cnt, trans->peer_fwd_cnt);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_get_credit);
+
+void virtio_transport_put_credit(struct virtio_transport *trans, u32 credit)
+{
+ mutex_lock(&trans->tx_lock);
+ trans->tx_cnt -= credit;
+ mutex_unlock(&trans->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_transport *trans = vsk->trans;
+ struct virtio_vsock_pkt_info info = {
+ .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE,
+ .type = type,
+ };
+
+ pr_debug("%s: sk=%p send_credit_update\n", __func__, vsk);
+ return trans->ops->send_pkt(vsk, &info);
+}
+
+static ssize_t
+virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
+ struct msghdr *msg,
+ size_t len)
+{
+ struct virtio_transport *trans = vsk->trans;
+ struct virtio_vsock_pkt *pkt;
+ size_t bytes, total = 0;
+ int err = -EFAULT;
+
+ mutex_lock(&trans->rx_lock);
+ while (total < len && trans->rx_bytes > 0 &&
+ !list_empty(&trans->rx_queue)) {
+ pkt = list_first_entry(&trans->rx_queue,
+ struct virtio_vsock_pkt, list);
+
+ bytes = len - total;
+ if (bytes > pkt->len - pkt->off)
+ bytes = pkt->len - pkt->off;
+
+ err = memcpy_to_msg(msg, pkt->buf + pkt->off, bytes);
+ if (err)
+ goto out;
+ total += bytes;
+ pkt->off += bytes;
+ if (pkt->off == pkt->len) {
+ virtio_transport_dec_rx_pkt(pkt);
+ list_del(&pkt->list);
+ virtio_transport_free_pkt(pkt);
+ }
+ }
+ mutex_unlock(&trans->rx_lock);
+
+ /* Send a credit pkt to peer */
+ virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM,
+ NULL);
+
+ return total;
+
+out:
+ mutex_unlock(&trans->rx_lock);
+ 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_transport *trans = vsk->trans;
+ s64 bytes;
+
+ mutex_lock(&trans->rx_lock);
+ bytes = trans->rx_bytes;
+ mutex_unlock(&trans->rx_lock);
+
+ return bytes;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_stream_has_data);
+
+static s64 virtio_transport_has_space(struct vsock_sock *vsk)
+{
+ struct virtio_transport *trans = vsk->trans;
+ s64 bytes;
+
+ bytes = trans->peer_buf_alloc - (trans->tx_cnt - trans->peer_fwd_cnt);
+ if (bytes < 0)
+ bytes = 0;
+
+ return bytes;
+}
+
+s64 virtio_transport_stream_has_space(struct vsock_sock *vsk)
+{
+ struct virtio_transport *trans = vsk->trans;
+ s64 bytes;
+
+ mutex_lock(&trans->tx_lock);
+ bytes = virtio_transport_has_space(vsk);
+ mutex_unlock(&trans->tx_lock);
+
+ pr_debug("%s: bytes=%lld\n", __func__, bytes);
+
+ 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_transport *trans;
+
+ trans = kzalloc(sizeof(*trans), GFP_KERNEL);
+ if (!trans)
+ return -ENOMEM;
+
+ vsk->trans = trans;
+ trans->vsk = vsk;
+ if (psk) {
+ struct virtio_transport *ptrans = psk->trans;
+ trans->buf_size = ptrans->buf_size;
+ trans->buf_size_min = ptrans->buf_size_min;
+ trans->buf_size_max = ptrans->buf_size_max;
+ trans->peer_buf_alloc = ptrans->peer_buf_alloc;
+ } else {
+ trans->buf_size = VIRTIO_VSOCK_DEFAULT_BUF_SIZE;
+ trans->buf_size_min = VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE;
+ trans->buf_size_max = VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE;
+ }
+
+ trans->buf_alloc = trans->buf_size;
+
+ pr_debug("%s: trans->buf_alloc=%d\n", __func__, trans->buf_alloc);
+
+ mutex_init(&trans->rx_lock);
+ mutex_init(&trans->tx_lock);
+ INIT_LIST_HEAD(&trans->rx_queue);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_do_socket_init);
+
+u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk)
+{
+ struct virtio_transport *trans = vsk->trans;
+
+ return trans->buf_size;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_get_buffer_size);
+
+u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk)
+{
+ struct virtio_transport *trans = vsk->trans;
+
+ return trans->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_transport *trans = vsk->trans;
+
+ return trans->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_transport *trans = vsk->trans;
+
+ if (val > VIRTIO_VSOCK_MAX_BUF_SIZE)
+ val = VIRTIO_VSOCK_MAX_BUF_SIZE;
+ if (val < trans->buf_size_min)
+ trans->buf_size_min = val;
+ if (val > trans->buf_size_max)
+ trans->buf_size_max = val;
+ trans->buf_size = val;
+ trans->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_transport *trans = vsk->trans;
+
+ if (val > VIRTIO_VSOCK_MAX_BUF_SIZE)
+ val = VIRTIO_VSOCK_MAX_BUF_SIZE;
+ if (val > trans->buf_size)
+ trans->buf_size = val;
+ trans->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_transport *trans = vsk->trans;
+
+ if (val > VIRTIO_VSOCK_MAX_BUF_SIZE)
+ val = VIRTIO_VSOCK_MAX_BUF_SIZE;
+ if (val < trans->buf_size)
+ trans->buf_size = val;
+ trans->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_transport *trans = vsk->trans;
+
+ return trans->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)
+{
+ /* Only allow guest->host connections */
+ return cid != VMADDR_CID_HOST;
+}
+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_transport *trans = vsk->trans;
+ struct virtio_vsock_pkt_info info = {
+ .op = VIRTIO_VSOCK_OP_REQUEST,
+ .type = VIRTIO_VSOCK_TYPE_STREAM,
+ };
+
+ pr_debug("%s: vsk=%p send_request\n", __func__, vsk);
+ return trans->ops->send_pkt(vsk, &info);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_connect);
+
+int virtio_transport_shutdown(struct vsock_sock *vsk, int mode)
+{
+ struct virtio_transport *trans = vsk->trans;
+ 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),
+ };
+
+ pr_debug("%s: vsk=%p: send_shutdown\n", __func__, vsk);
+ return trans->ops->send_pkt(vsk, &info);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_shutdown);
+
+void virtio_transport_release(struct vsock_sock *vsk)
+{
+ struct sock *sk = &vsk->sk;
+
+ pr_debug("%s: vsk=%p\n", __func__, vsk);
+
+ /* Tell other side to terminate connection */
+ if (sk->sk_type == SOCK_STREAM && sk->sk_state == SS_CONNECTED) {
+ virtio_transport_shutdown(vsk, SHUTDOWN_MASK);
+ }
+}
+EXPORT_SYMBOL_GPL(virtio_transport_release);
+
+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_transport *trans = vsk->trans;
+ struct virtio_vsock_pkt_info info = {
+ .op = VIRTIO_VSOCK_OP_RW,
+ .type = VIRTIO_VSOCK_TYPE_STREAM,
+ .msg = msg,
+ .pkt_len = len,
+ };
+
+ return trans->ops->send_pkt(vsk, &info);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_stream_enqueue);
+
+void virtio_transport_destruct(struct vsock_sock *vsk)
+{
+ struct virtio_transport *trans = vsk->trans;
+
+ pr_debug("%s: vsk=%p\n", __func__, vsk);
+ kfree(trans);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_destruct);
+
+static int virtio_transport_send_reset(struct vsock_sock *vsk,
+ struct virtio_vsock_pkt *pkt)
+{
+ struct virtio_transport *trans = vsk->trans;
+ struct virtio_vsock_pkt_info info = {
+ .op = VIRTIO_VSOCK_OP_RST,
+ .type = VIRTIO_VSOCK_TYPE_STREAM,
+ };
+
+ pr_debug("%s\n", __func__);
+
+ /* 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;
+
+ return trans->ops->send_pkt(vsk, &info);
+}
+
+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;
+
+ pr_debug("%s: vsk=%p\n", __func__, vsk);
+ switch (le16_to_cpu(pkt->hdr.op)) {
+ case VIRTIO_VSOCK_OP_RESPONSE:
+ pr_debug("%s: got RESPONSE\n", __func__);
+ 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:
+ pr_debug("%s: got invalid\n", __func__);
+ break;
+ case VIRTIO_VSOCK_OP_RST:
+ pr_debug("%s: got rst\n", __func__);
+ skerr = ECONNRESET;
+ err = 0;
+ goto destroy;
+ default:
+ pr_debug("%s: got def\n", __func__);
+ skerr = EPROTO;
+ err = -EINVAL;
+ goto destroy;
+ }
+ return 0;
+
+destroy:
+ virtio_transport_send_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_transport *trans = 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;
+ pkt->trans = trans;
+
+ mutex_lock(&trans->rx_lock);
+ virtio_transport_inc_rx_pkt(pkt);
+ list_add_tail(&pkt->list, &trans->rx_queue);
+ mutex_unlock(&trans->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:
+ pr_debug("%s: got shutdown\n", __func__);
+ 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 (le32_to_cpu(pkt->hdr.flags))
+ sk->sk_state_change(sk);
+ break;
+ case VIRTIO_VSOCK_OP_RST:
+ pr_debug("%s: got rst\n", __func__);
+ 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);
+ break;
+ default:
+ err = -EINVAL;
+ break;
+ }
+
+ virtio_transport_free_pkt(pkt);
+ return err;
+}
+
+static int
+virtio_transport_send_response(struct vsock_sock *vsk,
+ struct virtio_vsock_pkt *pkt)
+{
+ struct virtio_transport *trans = vsk->trans;
+ 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),
+ };
+
+ pr_debug("%s: send_response\n", __func__);
+
+ return trans->ops->send_pkt(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_send_reset(vsk, pkt);
+ return -EINVAL;
+ }
+
+ if (sk_acceptq_is_full(sk)) {
+ virtio_transport_send_reset(vsk, pkt);
+ return -ENOMEM;
+ }
+
+ pr_debug("%s: create pending\n", __func__);
+ child = __vsock_create(sock_net(sk), NULL, sk, GFP_KERNEL,
+ sk->sk_type, 0);
+ if (!child) {
+ virtio_transport_send_reset(vsk, pkt);
+ return -ENOMEM;
+ }
+
+ sk->sk_ack_backlog++;
+
+ lock_sock(child);
+
+ 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 void virtio_transport_space_update(struct sock *sk,
+ struct virtio_vsock_pkt *pkt)
+{
+ struct vsock_sock *vsk = vsock_sk(sk);
+ struct virtio_transport *trans = vsk->trans;
+ bool space_available;
+
+ /* buf_alloc and fwd_cnt is always included in the hdr */
+ mutex_lock(&trans->tx_lock);
+ trans->peer_buf_alloc = le32_to_cpu(pkt->hdr.buf_alloc);
+ trans->peer_fwd_cnt = le32_to_cpu(pkt->hdr.fwd_cnt);
+ space_available = virtio_transport_has_space(vsk);
+ mutex_unlock(&trans->tx_lock);
+
+ if (space_available)
+ sk->sk_write_space(sk);
+}
+
+/* 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 virtio_transport *trans;
+ struct sockaddr_vm src, dst;
+ struct vsock_sock *vsk;
+ struct sock *sk;
+
+ 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));
+
+ virtio_vsock_dumppkt(__func__, pkt);
+
+ if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) {
+ /* TODO send RST */
+ 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) {
+ pr_debug("%s: can not find bound_socket\n", __func__);
+ virtio_vsock_dumppkt(__func__, pkt);
+ /* Ignore this pkt instead of sending reset back */
+ /* TODO send a RST unless this packet is a RST (to avoid infinite loops) */
+ goto free_pkt;
+ }
+ }
+
+ vsk = vsock_sk(sk);
+ trans = vsk->trans;
+ BUG_ON(!trans);
+
+ virtio_transport_space_update(sk, pkt);
+
+ lock_sock(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;
+ 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");
--
2.5.0
_______________________________________________
Virtualization mailing list
Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
