#include <linux/hyperv.h>
#include <net/sock.h>
#include <net/af_vsock.h>
+#include <asm/hyperv-tlfs.h>
/* Older (VMBUS version 'VERSION_WIN10' or before) Windows hosts have some
- * stricter requirements on the hv_sock ring buffer size of six 4K pages. Newer
- * hosts don't have this limitation; but, keep the defaults the same for compat.
+ * stricter requirements on the hv_sock ring buffer size of six 4K pages.
+ * hyperv-tlfs defines HV_HYP_PAGE_SIZE as 4K. Newer hosts don't have this
+ * limitation; but, keep the defaults the same for compat.
*/
-#define PAGE_SIZE_4K 4096
-#define RINGBUFFER_HVS_RCV_SIZE (PAGE_SIZE_4K * 6)
-#define RINGBUFFER_HVS_SND_SIZE (PAGE_SIZE_4K * 6)
-#define RINGBUFFER_HVS_MAX_SIZE (PAGE_SIZE_4K * 64)
+#define RINGBUFFER_HVS_RCV_SIZE (HV_HYP_PAGE_SIZE * 6)
+#define RINGBUFFER_HVS_SND_SIZE (HV_HYP_PAGE_SIZE * 6)
+#define RINGBUFFER_HVS_MAX_SIZE (HV_HYP_PAGE_SIZE * 64)
/* The MTU is 16KB per the host side's design */
#define HVS_MTU_SIZE (1024 * 16)
* ringbuffer APIs that allow us to directly copy data from userspace buffer
* to VMBus ringbuffer.
*/
-#define HVS_SEND_BUF_SIZE (PAGE_SIZE_4K - sizeof(struct vmpipe_proto_header))
+#define HVS_SEND_BUF_SIZE \
+ (HV_HYP_PAGE_SIZE - sizeof(struct vmpipe_proto_header))
struct hvs_send_buf {
/* The header before the payload data */
****************************************************************************
* The only valid Service GUIDs, from the perspectives of both the host and *
* Linux VM, that can be connected by the other end, must conform to this *
- * format: <port>-facb-11e6-bd58-64006a7986d3, and the "port" must be in *
- * this range [0, 0x7FFFFFFF]. *
+ * format: <port>-facb-11e6-bd58-64006a7986d3. *
****************************************************************************
*
* When we write apps on the host to connect(), the GUID ServiceID is used.
* When we write apps in Linux VM to connect(), we only need to specify the
* port and the driver will form the GUID and use that to request the host.
*
- * From the perspective of Linux VM:
- * 1. the local ephemeral port (i.e. the local auto-bound port when we call
- * connect() without explicit bind()) is generated by __vsock_bind_stream(),
- * and the range is [1024, 0xFFFFFFFF).
- * 2. the remote ephemeral port (i.e. the auto-generated remote port for
- * a connect request initiated by the host's connect()) is generated by
- * hvs_remote_addr_init() and the range is [0x80000000, 0xFFFFFFFF).
*/
-#define MAX_LISTEN_PORT ((u32)0x7FFFFFFF)
-#define MAX_VM_LISTEN_PORT MAX_LISTEN_PORT
-#define MAX_HOST_LISTEN_PORT MAX_LISTEN_PORT
-#define MIN_HOST_EPHEMERAL_PORT (MAX_HOST_LISTEN_PORT + 1)
-
/* 00000000-facb-11e6-bd58-64006a7986d3 */
static const guid_t srv_id_template =
GUID_INIT(0x00000000, 0xfacb, 0x11e6, 0xbd, 0x58,
0x64, 0x00, 0x6a, 0x79, 0x86, 0xd3);
+static bool hvs_check_transport(struct vsock_sock *vsk);
+
static bool is_valid_srv_id(const guid_t *id)
{
return !memcmp(&id->b[4], &srv_id_template.b[4], sizeof(guid_t) - 4);
vsock_addr_init(addr, VMADDR_CID_ANY, port);
}
-static void hvs_remote_addr_init(struct sockaddr_vm *remote,
- struct sockaddr_vm *local)
-{
- static u32 host_ephemeral_port = MIN_HOST_EPHEMERAL_PORT;
- struct sock *sk;
-
- vsock_addr_init(remote, VMADDR_CID_ANY, VMADDR_PORT_ANY);
-
- while (1) {
- /* Wrap around ? */
- if (host_ephemeral_port < MIN_HOST_EPHEMERAL_PORT ||
- host_ephemeral_port == VMADDR_PORT_ANY)
- host_ephemeral_port = MIN_HOST_EPHEMERAL_PORT;
-
- remote->svm_port = host_ephemeral_port++;
-
- sk = vsock_find_connected_socket(remote, local);
- if (!sk) {
- /* Found an available ephemeral port */
- return;
- }
-
- /* Release refcnt got in vsock_find_connected_socket */
- sock_put(sk);
- }
-}
-
static void hvs_set_channel_pending_send_size(struct vmbus_channel *chan)
{
set_channel_pending_send_size(chan,
if_type = &chan->offermsg.offer.if_type;
if_instance = &chan->offermsg.offer.if_instance;
conn_from_host = chan->offermsg.offer.u.pipe.user_def[0];
-
- /* The host or the VM should only listen on a port in
- * [0, MAX_LISTEN_PORT]
- */
- if (!is_valid_srv_id(if_type) ||
- get_port_by_srv_id(if_type) > MAX_LISTEN_PORT)
+ if (!is_valid_srv_id(if_type))
return;
hvs_addr_init(&addr, conn_from_host ? if_type : if_instance);
if (sk->sk_ack_backlog >= sk->sk_max_ack_backlog)
goto out;
- new = __vsock_create(sock_net(sk), NULL, sk, GFP_KERNEL,
- sk->sk_type, 0);
+ new = vsock_create_connected(sk);
if (!new)
goto out;
new->sk_state = TCP_SYN_SENT;
vnew = vsock_sk(new);
+
+ hvs_addr_init(&vnew->local_addr, if_type);
+
+ /* Remote peer is always the host */
+ vsock_addr_init(&vnew->remote_addr,
+ VMADDR_CID_HOST, VMADDR_PORT_ANY);
+ vnew->remote_addr.svm_port = get_port_by_srv_id(if_instance);
+ ret = vsock_assign_transport(vnew, vsock_sk(sk));
+ /* Transport assigned (looking at remote_addr) must be the
+ * same where we received the request.
+ */
+ if (ret || !hvs_check_transport(vnew)) {
+ sock_put(new);
+ goto out;
+ }
hvs_new = vnew->trans;
hvs_new->chan = chan;
} else {
} else {
sndbuf = max_t(int, sk->sk_sndbuf, RINGBUFFER_HVS_SND_SIZE);
sndbuf = min_t(int, sndbuf, RINGBUFFER_HVS_MAX_SIZE);
- sndbuf = ALIGN(sndbuf, PAGE_SIZE);
+ sndbuf = ALIGN(sndbuf, HV_HYP_PAGE_SIZE);
rcvbuf = max_t(int, sk->sk_rcvbuf, RINGBUFFER_HVS_RCV_SIZE);
rcvbuf = min_t(int, rcvbuf, RINGBUFFER_HVS_MAX_SIZE);
- rcvbuf = ALIGN(rcvbuf, PAGE_SIZE);
+ rcvbuf = ALIGN(rcvbuf, HV_HYP_PAGE_SIZE);
}
ret = vmbus_open(chan, sndbuf, rcvbuf, NULL, 0, hvs_channel_cb,
if (conn_from_host) {
new->sk_state = TCP_ESTABLISHED;
- sk->sk_ack_backlog++;
-
- hvs_addr_init(&vnew->local_addr, if_type);
- hvs_remote_addr_init(&vnew->remote_addr, &vnew->local_addr);
+ sk_acceptq_added(sk);
hvs_new->vm_srv_id = *if_type;
hvs_new->host_srv_id = *if_instance;
ssize_t ret = 0;
ssize_t bytes_written = 0;
- BUILD_BUG_ON(sizeof(*send_buf) != PAGE_SIZE_4K);
+ BUILD_BUG_ON(sizeof(*send_buf) != HV_HYP_PAGE_SIZE);
send_buf = kmalloc(sizeof(*send_buf), GFP_KERNEL);
if (!send_buf)
static bool hvs_stream_allow(u32 cid, u32 port)
{
- /* The host's port range [MIN_HOST_EPHEMERAL_PORT, 0xFFFFFFFF) is
- * reserved as ephemeral ports, which are used as the host's ports
- * when the host initiates connections.
- *
- * Perform this check in the guest so an immediate error is produced
- * instead of a timeout.
- */
- if (port > MAX_HOST_LISTEN_PORT)
- return false;
-
if (cid == VMADDR_CID_HOST)
return true;
return 0;
}
-static void hvs_set_buffer_size(struct vsock_sock *vsk, u64 val)
-{
- /* Ignored. */
-}
-
-static void hvs_set_min_buffer_size(struct vsock_sock *vsk, u64 val)
-{
- /* Ignored. */
-}
-
-static void hvs_set_max_buffer_size(struct vsock_sock *vsk, u64 val)
-{
- /* Ignored. */
-}
-
-static u64 hvs_get_buffer_size(struct vsock_sock *vsk)
-{
- return -ENOPROTOOPT;
-}
-
-static u64 hvs_get_min_buffer_size(struct vsock_sock *vsk)
-{
- return -ENOPROTOOPT;
-}
-
-static u64 hvs_get_max_buffer_size(struct vsock_sock *vsk)
-{
- return -ENOPROTOOPT;
-}
-
static struct vsock_transport hvs_transport = {
+ .module = THIS_MODULE,
+
.get_local_cid = hvs_get_local_cid,
.init = hvs_sock_init,
.notify_send_pre_enqueue = hvs_notify_send_pre_enqueue,
.notify_send_post_enqueue = hvs_notify_send_post_enqueue,
- .set_buffer_size = hvs_set_buffer_size,
- .set_min_buffer_size = hvs_set_min_buffer_size,
- .set_max_buffer_size = hvs_set_max_buffer_size,
- .get_buffer_size = hvs_get_buffer_size,
- .get_min_buffer_size = hvs_get_min_buffer_size,
- .get_max_buffer_size = hvs_get_max_buffer_size,
};
+static bool hvs_check_transport(struct vsock_sock *vsk)
+{
+ return vsk->transport == &hvs_transport;
+}
+
static int hvs_probe(struct hv_device *hdev,
const struct hv_vmbus_device_id *dev_id)
{
return 0;
}
+/* hv_sock connections can not persist across hibernation, and all the hv_sock
+ * channels are forced to be rescinded before hibernation: see
+ * vmbus_bus_suspend(). Here the dummy hvs_suspend() and hvs_resume()
+ * are only needed because hibernation requires that every vmbus device's
+ * driver should have a .suspend and .resume callback: see vmbus_suspend().
+ */
+static int hvs_suspend(struct hv_device *hv_dev)
+{
+ /* Dummy */
+ return 0;
+}
+
+static int hvs_resume(struct hv_device *dev)
+{
+ /* Dummy */
+ return 0;
+}
+
/* This isn't really used. See vmbus_match() and vmbus_probe() */
static const struct hv_vmbus_device_id id_table[] = {
{},
.id_table = id_table,
.probe = hvs_probe,
.remove = hvs_remove,
+ .suspend = hvs_suspend,
+ .resume = hvs_resume,
};
static int __init hvs_init(void)
if (ret != 0)
return ret;
- ret = vsock_core_init(&hvs_transport);
+ ret = vsock_core_register(&hvs_transport, VSOCK_TRANSPORT_F_G2H);
if (ret) {
vmbus_driver_unregister(&hvs_drv);
return ret;
static void __exit hvs_exit(void)
{
- vsock_core_exit();
+ vsock_core_unregister(&hvs_transport);
vmbus_driver_unregister(&hvs_drv);
}