Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 5b815b52 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'vsock' 



Andy King says:

====================
In an effort to improve the out-of-the-box experience with Linux kernels for
VMware users, VMware is working on readying the VM Sockets (VSOCK, formerly
VMCI Sockets) (vsock) kernel module for inclusion in the Linux kernel. The
purpose of this post is to acquire feedback on the vsock kernel module.

Unlike previous submissions, where the new socket family was entirely reliant
on VMware's VMCI PCI device (and thus VMware's hypervisor), VM Sockets is now
completely[1] separated out into two parts, each in its own module:

o Core socket code, which is transport-neutral and invokes transport
  callbacks to communicate with the hypervisor.  This is vsock.ko.
o A VMCI transport, which communicates over VMCI with the VMware hypervisor.
  This is vmw_vsock_vmci_transport.ko, and it registers with the core module
  as a transport.

This should provide a path to introducing additional transports, for example
virtio, with the ultimate goal being to make this new socket family
hypervisor-neutral.

[1] If Gerd tries it and determines this to be false (still), I'll ship him
    a keg of beer.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents fd502311 d021c344

include/linux/socket.h

+3 −1
Original line number Diff line number Diff line
@@ -178,7 +178,8 @@ struct ucred { 
#define AF_CAIF		37	/* CAIF sockets			*/

#define AF_ALG		38	/* Algorithm sockets		*/

#define AF_NFC		39	/* NFC sockets			*/

#define AF_MAX		40	/* For now.. */

#define AF_VSOCK	40	/* vSockets			*/

#define AF_MAX		41	/* For now.. */



/* Protocol families, same as address families. */

#define PF_UNSPEC	AF_UNSPEC
@@ -221,6 +222,7 @@ struct ucred { 
#define PF_CAIF		AF_CAIF

#define PF_ALG		AF_ALG

#define PF_NFC		AF_NFC

#define PF_VSOCK	AF_VSOCK

#define PF_MAX		AF_MAX



/* Maximum queue length specifiable by listen.  */

include/uapi/linux/vm_sockets.h

0 → 100644
+171 −0
Original line number Diff line number Diff line 
/*

 * VMware vSockets Driver

 *

 * Copyright (C) 2007-2013 VMware, Inc. All rights reserved.

 *

 * This program is free software; you can redistribute it and/or modify it

 * under the terms of the GNU General Public License as published by the Free

 * Software Foundation version 2 and no later version.

 *

 * This program is distributed in the hope that it will be useful, but WITHOUT

 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or

 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for

 * more details.

 */



#ifndef _VM_SOCKETS_H_

#define _VM_SOCKETS_H_



#if !defined(__KERNEL__)

#include <sys/socket.h>

#endif



/* Option name for STREAM socket buffer size.  Use as the option name in

 * setsockopt(3) or getsockopt(3) to set or get an unsigned long long that

 * specifies the size of the buffer underlying a vSockets STREAM socket.

 * Value is clamped to the MIN and MAX.

 */



#define SO_VM_SOCKETS_BUFFER_SIZE 0



/* Option name for STREAM socket minimum buffer size.  Use as the option name

 * in setsockopt(3) or getsockopt(3) to set or get an unsigned long long that

 * specifies the minimum size allowed for the buffer underlying a vSockets

 * STREAM socket.

 */



#define SO_VM_SOCKETS_BUFFER_MIN_SIZE 1



/* Option name for STREAM socket maximum buffer size.  Use as the option name

 * in setsockopt(3) or getsockopt(3) to set or get an unsigned long long

 * that specifies the maximum size allowed for the buffer underlying a

 * vSockets STREAM socket.

 */



#define SO_VM_SOCKETS_BUFFER_MAX_SIZE 2



/* Option name for socket peer's host-specific VM ID.  Use as the option name

 * in getsockopt(3) to get a host-specific identifier for the peer endpoint's

 * VM.  The identifier is a signed integer.

 * Only available for hypervisor endpoints.

 */



#define SO_VM_SOCKETS_PEER_HOST_VM_ID 3



/* Option name for socket's service label.  Use as the option name in

 * setsockopt(3) or getsockopt(3) to set or get the service label for a socket.

 * The service label is a C-style NUL-terminated string.  Only available for

 * hypervisor endpoints.

 */



#define SO_VM_SOCKETS_SERVICE_LABEL 4



/* Option name for determining if a socket is trusted.  Use as the option name

 * in getsockopt(3) to determine if a socket is trusted.  The value is a

 * signed integer.

 */



#define SO_VM_SOCKETS_TRUSTED 5



/* Option name for STREAM socket connection timeout.  Use as the option name

 * in setsockopt(3) or getsockopt(3) to set or get the connection

 * timeout for a STREAM socket.

 */



#define SO_VM_SOCKETS_CONNECT_TIMEOUT 6



/* Option name for using non-blocking send/receive.  Use as the option name

 * for setsockopt(3) or getsockopt(3) to set or get the non-blocking

 * transmit/receive flag for a STREAM socket.  This flag determines whether

 * send() and recv() can be called in non-blocking contexts for the given

 * socket.  The value is a signed integer.

 *

 * This option is only relevant to kernel endpoints, where descheduling the

 * thread of execution is not allowed, for example, while holding a spinlock.

 * It is not to be confused with conventional non-blocking socket operations.

 *

 * Only available for hypervisor endpoints.

 */



#define SO_VM_SOCKETS_NONBLOCK_TXRX 7



/* The vSocket equivalent of INADDR_ANY.  This works for the svm_cid field of

 * sockaddr_vm and indicates the context ID of the current endpoint.

 */



#define VMADDR_CID_ANY -1U



/* Bind to any available port.  Works for the svm_port field of

 * sockaddr_vm.

 */



#define VMADDR_PORT_ANY -1U



/* Use this as the destination CID in an address when referring to the

 * hypervisor.  VMCI relies on it being 0, but this would be useful for other

 * transports too.

 */



#define VMADDR_CID_HYPERVISOR 0



/* This CID is specific to VMCI and can be considered reserved (even VMCI

 * doesn't use it anymore, it's a legacy value from an older release).

 */



#define VMADDR_CID_RESERVED 1



/* Use this as the destination CID in an address when referring to the host

 * (any process other than the hypervisor).  VMCI relies on it being 2, but

 * this would be useful for other transports too.

 */



#define VMADDR_CID_HOST 2



/* Invalid vSockets version. */



#define VM_SOCKETS_INVALID_VERSION -1U



/* The epoch (first) component of the vSockets version.  A single byte

 * representing the epoch component of the vSockets version.

 */



#define VM_SOCKETS_VERSION_EPOCH(_v) (((_v) & 0xFF000000) >> 24)



/* The major (second) component of the vSockets version.   A single byte

 * representing the major component of the vSockets version.  Typically

 * changes for every major release of a product.

 */



#define VM_SOCKETS_VERSION_MAJOR(_v) (((_v) & 0x00FF0000) >> 16)



/* The minor (third) component of the vSockets version.  Two bytes representing

 * the minor component of the vSockets version.

 */



#define VM_SOCKETS_VERSION_MINOR(_v) (((_v) & 0x0000FFFF))



/* Address structure for vSockets.   The address family should be set to

 * whatever vmci_sock_get_af_value_fd() returns.  The structure members should

 * all align on their natural boundaries without resorting to compiler packing

 * directives.  The total size of this structure should be exactly the same as

 * that of struct sockaddr.

 */



struct sockaddr_vm {

	sa_family_t svm_family;

	unsigned short svm_reserved1;

	unsigned int svm_port;

	unsigned int svm_cid;

	unsigned char svm_zero[sizeof(struct sockaddr) -

			       sizeof(sa_family_t) -

			       sizeof(unsigned short) -

			       sizeof(unsigned int) - sizeof(unsigned int)];

};



#define IOCTL_VM_SOCKETS_GET_LOCAL_CID		_IO(7, 0xb9)



#if defined(__KERNEL__)

int vm_sockets_get_local_cid(void);

#endif



#endif

net/Kconfig

+1 −0
Original line number Diff line number Diff line
@@ -217,6 +217,7 @@ source "net/dcb/Kconfig" 
source "net/dns_resolver/Kconfig"

source "net/batman-adv/Kconfig"

source "net/openvswitch/Kconfig"

source "net/vmw_vsock/Kconfig"



config RPS

	boolean

net/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -69,3 +69,4 @@ obj-$(CONFIG_CEPH_LIB) += ceph/ 
obj-$(CONFIG_BATMAN_ADV)	+= batman-adv/

obj-$(CONFIG_NFC)		+= nfc/

obj-$(CONFIG_OPENVSWITCH)	+= openvswitch/

obj-$(CONFIG_VSOCKETS)	+= vmw_vsock/

net/vmw_vsock/Kconfig

0 → 100644
+28 −0
Original line number Diff line number Diff line 
#

# Vsock protocol

#



config VSOCKETS

	tristate "Virtual Socket protocol"

	help

	  Virtual Socket Protocol is a socket protocol similar to TCP/IP

	  allowing comunication between Virtual Machines and hypervisor

	  or host.



	  You should also select one or more hypervisor-specific transports

	  below.



	  To compile this driver as a module, choose M here: the module

	  will be called vsock. If unsure, say N.



config VMWARE_VMCI_VSOCKETS

	tristate "VMware VMCI transport for Virtual Sockets"

	depends on VSOCKETS && VMWARE_VMCI

	help

	  This module implements a VMCI transport for Virtual Sockets.



	  Enable this transport if your Virtual Machine runs on a VMware

	  hypervisor.



	  To compile this driver as a module, choose M here: the module

	  will be called vmw_vsock_vmci_transport. If unsure, say N.