Merge branch 'vsock-add-multi-transports-support'

Stefano Garzarella says:

====================
vsock: add multi-transports support

Most of the patches are reviewed by Dexuan, Stefan, and Jorgen.
The following patches need reviews:
- [11/15] vsock: add multi-transports support
- [12/15] vsock/vmci: register vmci_transport only when VMCI guest/host
          are active
- [15/15] vhost/vsock: refuse CID assigned to the guest->host transport

RFC: https://patchwork.ozlabs.org/cover/1168442/
v1: https://patchwork.ozlabs.org/cover/1181986/

v1 -> v2:
- Patch 11:
    + vmci_transport: sent reset when vsock_assign_transport() fails
      [Jorgen]
    + fixed loopback in the guests, checking if the remote_addr is the
      same of transport_g2h->get_local_cid()
    + virtio_transport_common: updated space available while creating
      the new child socket during a connection request
- Patch 12:
    + removed 'features' variable in vmci_transport_init() [Stefan]
    + added a flag to register only once the host [Jorgen]
- Added patch 15 to refuse CID assigned to the guest->host transport in
  the vhost_transport

This series adds the multi-transports support to vsock, following
this proposal: https://www.spinics.net/lists/netdev/msg575792.html

With the multi-transports support, we can use VSOCK with nested VMs
(using also different hypervisors) loading both guest->host and
host->guest transports at the same time.
Before this series, vmci_transport supported this behavior but only
using VMware hypervisor on L0, L1, etc.

The first 9 patches are cleanups and preparations, maybe some of
these can go regardless of this series.

Patch 10 changes the hvs_remote_addr_init(). setting the
VMADDR_CID_HOST as remote CID instead of VMADDR_CID_ANY to make
the choice of transport to be used work properly.

Patch 11 adds multi-transports support.

Patch 12 changes a little bit the vmci_transport and the vmci driver
to register the vmci_transport only when there are active host/guest.

Patch 13 prevents the transport modules unloading while sockets are
assigned to them.

Patch 14 fixes an issue in the bind() logic discoverable only with
the new multi-transport support.

Patch 15 refuses CID assigned to the guest->host transport in the
vhost_transport.

I've tested this series with nested KVM (vsock-transport [L0,L1],
virtio-transport[L1,L2]) and with VMware (L0) + KVM (L1)
(vmci-transport [L0,L1], vhost-transport [L1], virtio-transport[L2]).

Dexuan successfully tested the RFC series on HyperV with a Linux guest.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 31 insertions, 51 deletions

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 07875ccc7bb5..71c81e0dc8f2 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -7,9 +7,6 @@
 #include <net/sock.h>
 #include <net/af_vsock.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)
@@ -25,11 +22,6 @@ enum {
 struct virtio_vsock_sock {
 	struct vsock_sock *vsk;
 
-	/* Protected by lock_sock(sk_vsock(trans->vsk)) */
-	u32 buf_size;
-	u32 buf_size_min;
-	u32 buf_size_max;
-
 	spinlock_t tx_lock;
 	spinlock_t rx_lock;
 
@@ -92,12 +84,6 @@ 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,
@@ -124,6 +110,7 @@ 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);
+void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val);
 
 u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk);
 bool virtio_transport_stream_is_active(struct vsock_sock *vsk);
@@ -150,7 +137,8 @@ virtio_transport_dgram_enqueue(struct vsock_sock *vsk,
 
 void virtio_transport_destruct(struct vsock_sock *vsk);
 
-void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt);
+void virtio_transport_recv_pkt(struct virtio_transport *t,
+			       struct virtio_vsock_pkt *pkt);
 void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt);
 void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt);
 u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted);
diff --git a/include/linux/vm_sockets.h b/include/linux/vm_sockets.h
deleted file mode 100644
index 33f1a2ecd905..000000000000
--- a/include/linux/vm_sockets.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * VMware vSockets Driver
- *
- * Copyright (C) 2007-2013 VMware, Inc. All rights reserved.
- */
-
-#ifndef _VM_SOCKETS_H
-#define _VM_SOCKETS_H
-
-#include <uapi/linux/vm_sockets.h>
-
-int vm_sockets_get_local_cid(void);
-
-#endif /* _VM_SOCKETS_H */
diff --git a/include/linux/vmw_vmci_api.h b/include/linux/vmw_vmci_api.h
index acd9fafe4fc6..f28907345c80 100644
--- a/include/linux/vmw_vmci_api.h
+++ b/include/linux/vmw_vmci_api.h
@@ -19,6 +19,7 @@
 struct msghdr;
 typedef void (vmci_device_shutdown_fn) (void *device_registration,
 					void *user_data);
+typedef void (*vmci_vsock_cb) (bool is_host);
 
 int vmci_datagram_create_handle(u32 resource_id, u32 flags,
 				vmci_datagram_recv_cb recv_cb,
@@ -37,6 +38,7 @@ int vmci_doorbell_destroy(struct vmci_handle handle);
 int vmci_doorbell_notify(struct vmci_handle handle, u32 priv_flags);
 u32 vmci_get_context_id(void);
 bool vmci_is_context_owner(u32 context_id, kuid_t uid);
+int vmci_register_vsock_callback(vmci_vsock_cb callback);
 
 int vmci_event_subscribe(u32 event,
 			 vmci_event_cb callback, void *callback_data,
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 80ea0f93d3f7..4206dc6d813f 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -10,7 +10,7 @@
 
 #include <linux/kernel.h>
 #include <linux/workqueue.h>
-#include <linux/vm_sockets.h>
+#include <uapi/linux/vm_sockets.h>
 
 #include "vsock_addr.h"
 
@@ -27,6 +27,7 @@ extern spinlock_t vsock_table_lock;
 struct vsock_sock {
 	/* sk must be the first member. */
 	struct sock sk;
+	const struct vsock_transport *transport;
 	struct sockaddr_vm local_addr;
 	struct sockaddr_vm remote_addr;
 	/* Links for the global tables of bound and connected sockets. */
@@ -64,16 +65,18 @@ struct vsock_sock {
 	bool sent_request;
 	bool ignore_connecting_rst;
 
+	/* Protected by lock_sock(sk) */
+	u64 buffer_size;
+	u64 buffer_min_size;
+	u64 buffer_max_size;
+
 	/* Private to transport. */
 	void *trans;
 };
 
 s64 vsock_stream_has_data(struct vsock_sock *vsk);
 s64 vsock_stream_has_space(struct vsock_sock *vsk);
-struct sock *__vsock_create(struct net *net,
-			    struct socket *sock,
-			    struct sock *parent,
-			    gfp_t priority, unsigned short type, int kern);
+struct sock *vsock_create_connected(struct sock *parent);
 
 /**** TRANSPORT ****/
 
@@ -88,7 +91,17 @@ struct vsock_transport_send_notify_data {
 	u64 data2; /* Transport-defined. */
 };
 
+/* Transport features flags */
+/* Transport provides host->guest communication */
+#define VSOCK_TRANSPORT_F_H2G		0x00000001
+/* Transport provides guest->host communication */
+#define VSOCK_TRANSPORT_F_G2H		0x00000002
+/* Transport provides DGRAM communication */
+#define VSOCK_TRANSPORT_F_DGRAM		0x00000004
+
 struct vsock_transport {
+	struct module *module;
+
 	/* Initialize/tear-down socket. */
 	int (*init)(struct vsock_sock *, struct vsock_sock *);
 	void (*destruct)(struct vsock_sock *);
@@ -139,33 +152,23 @@ struct vsock_transport {
 		struct vsock_transport_send_notify_data *);
 	int (*notify_send_post_enqueue)(struct vsock_sock *, ssize_t,
 		struct vsock_transport_send_notify_data *);
+	/* sk_lock held by the caller */
+	void (*notify_buffer_size)(struct vsock_sock *, u64 *);
 
 	/* Shutdown. */
 	int (*shutdown)(struct vsock_sock *, int);
 
-	/* Buffer sizes. */
-	void (*set_buffer_size)(struct vsock_sock *, u64);
-	void (*set_min_buffer_size)(struct vsock_sock *, u64);
-	void (*set_max_buffer_size)(struct vsock_sock *, u64);
-	u64 (*get_buffer_size)(struct vsock_sock *);
-	u64 (*get_min_buffer_size)(struct vsock_sock *);
-	u64 (*get_max_buffer_size)(struct vsock_sock *);
-
 	/* Addressing. */
 	u32 (*get_local_cid)(void);
 };
 
 /**** CORE ****/
 
-int __vsock_core_init(const struct vsock_transport *t, struct module *owner);
-static inline int vsock_core_init(const struct vsock_transport *t)
-{
-	return __vsock_core_init(t, THIS_MODULE);
-}
-void vsock_core_exit(void);
+int vsock_core_register(const struct vsock_transport *t, int features);
+void vsock_core_unregister(const struct vsock_transport *t);
 
 /* The transport may downcast this to access transport-specific functions */
-const struct vsock_transport *vsock_core_get_transport(void);
+const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk);
 
 /**** UTILS ****/
 
@@ -193,6 +196,8 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
 					 struct sockaddr_vm *dst);
 void vsock_remove_sock(struct vsock_sock *vsk);
 void vsock_for_each_connected_socket(void (*fn)(struct sock *sk));
+int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk);
+bool vsock_find_cid(unsigned int cid);
 
 /**** TAP ****/
 
diff --git a/include/net/vsock_addr.h b/include/net/vsock_addr.h
index 57d2db5c4bdf..cf8cc140d68d 100644
--- a/include/net/vsock_addr.h
+++ b/include/net/vsock_addr.h
@@ -8,7 +8,7 @@
 #ifndef _VSOCK_ADDR_H_
 #define _VSOCK_ADDR_H_
 
-#include <linux/vm_sockets.h>
+#include <uapi/linux/vm_sockets.h>
 
 void vsock_addr_init(struct sockaddr_vm *addr, u32 cid, u32 port);
 int vsock_addr_validate(const struct sockaddr_vm *addr);