@@ -70,6 +70,7 @@ Code Seq#(hex) Include File Comments
0x03 all linux/hdreg.h
0x04 D2-DC linux/umsdos_fs.h Dead since 2.6.11, but don't reuse these.
0x06 all linux/lp.h
+0x07 9F-D0 linux/vmw_vmci_defs.h <mailto:georgezhang@vmware.com>
0x09 all linux/raid/md_u.h
0x10 00-0F drivers/char/s390/vmcp.h
0x12 all linux/fs.h
@@ -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 /* VMCI sockets */
+#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. */
@@ -218,6 +218,7 @@ 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
@@ -70,3 +70,4 @@ obj-$(CONFIG_CEPH_LIB) += ceph/
obj-$(CONFIG_BATMAN_ADV) += batman-adv/
obj-$(CONFIG_NFC) += nfc/
obj-$(CONFIG_OPENVSWITCH) += openvswitch/
+obj-$(CONFIG_VMWARE_VSOCK) += vmw_vsock/
new file mode 100644
@@ -0,0 +1,14 @@
+#
+# Vsock protocol
+#
+
+config VMWARE_VSOCK
+ tristate "Virtual Socket protocol"
+ depends on VMWARE_VMCI
+ help
+ Virtual Socket Protocol is a socket protocol similar to TCP/IP
+ allowing comunication between Virtual Machines and VMware
+ hypervisor.
+
+ To compile this driver as a module, choose M here: the module
+ will be called vsock. If unsure, say N.
new file mode 100644
@@ -0,0 +1,4 @@
+obj-$(CONFIG_VMWARE_VSOCK) += vmw_vsock.o
+
+vmw_vsock-y += af_vsock.o notify.o notify_qstate.o stats.o util.o \
+ vsock_addr.o
new file mode 100644
@@ -0,0 +1,408 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2009-2012 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.
+ */
+
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/stddef.h>
+#include <net/sock.h>
+
+#include "notify.h"
+#include "af_vsock.h"
+
+#define PKT_FIELD(vsk, field_name) ((vsk)->notify.pkt_q_state.field_name)
+
+static bool vsock_vmci_notify_waiting_write(struct vsock_vmci_sock *vsk)
+{
+ bool retval;
+ u64 notify_limit;
+
+ if (!PKT_FIELD(vsk, peer_waiting_write))
+ return false;
+
+ /* When the sender blocks, we take that as a sign that the sender is
+ * faster than the receiver. To reduce the transmit rate of the sender,
+ * we delay the sending of the read notification by decreasing the
+ * write_notify_window. The notification is delayed until the number of
+ * bytes used in the queue drops below the write_notify_window.
+ */
+
+ if (!PKT_FIELD(vsk, peer_waiting_write_detected)) {
+ PKT_FIELD(vsk, peer_waiting_write_detected) = true;
+ if (PKT_FIELD(vsk, write_notify_window) < PAGE_SIZE) {
+ PKT_FIELD(vsk, write_notify_window) =
+ PKT_FIELD(vsk, write_notify_min_window);
+ } else {
+ PKT_FIELD(vsk, write_notify_window) -= PAGE_SIZE;
+ if (PKT_FIELD(vsk, write_notify_window) <
+ PKT_FIELD(vsk, write_notify_min_window))
+ PKT_FIELD(vsk, write_notify_window) =
+ PKT_FIELD(vsk, write_notify_min_window);
+
+ }
+ }
+ notify_limit = vsk->consume_size - PKT_FIELD(vsk, write_notify_window);
+
+ /* The notify_limit is used to delay notifications in the case where
+ * flow control is enabled. Below the test is expressed in terms of
+ * free space in the queue: if free_space > ConsumeSize -
+ * write_notify_window then notify An alternate way of expressing this
+ * is to rewrite the expression to use the data ready in the receive
+ * queue: if write_notify_window > bufferReady then notify as
+ * free_space == ConsumeSize - bufferReady.
+ */
+
+ retval = vmci_qpair_consume_free_space(vsk->qpair) > notify_limit;
+
+ if (retval) {
+ /* Once we notify the peer, we reset the detected flag so the
+ * next wait will again cause a decrease in the window size.
+ */
+
+ PKT_FIELD(vsk, peer_waiting_write_detected) = false;
+ }
+ return retval;
+}
+
+static void
+vsock_vmci_handle_read(struct sock *sk,
+ struct vsock_packet *pkt,
+ bool bottom_half,
+ struct sockaddr_vm *dst, struct sockaddr_vm *src)
+{
+
+ sk->sk_write_space(sk);
+}
+
+static void
+vsock_vmci_handle_wrote(struct sock *sk,
+ struct vsock_packet *pkt,
+ bool bottom_half,
+ struct sockaddr_vm *dst, struct sockaddr_vm *src)
+{
+ sk->sk_data_ready(sk, 0);
+}
+
+static void vsock_vmci_block_update_write_window(struct sock *sk)
+{
+ struct vsock_vmci_sock *vsk;
+
+ vsk = vsock_sk(sk);
+
+ if (PKT_FIELD(vsk, write_notify_window) < vsk->consume_size)
+ PKT_FIELD(vsk, write_notify_window) =
+ min(PKT_FIELD(vsk, write_notify_window) + PAGE_SIZE,
+ vsk->consume_size);
+
+}
+
+static int vsock_vmci_send_read_notification(struct sock *sk)
+{
+ struct vsock_vmci_sock *vsk;
+ bool sent_read;
+ unsigned int retries;
+ int err;
+
+ vsk = vsock_sk(sk);
+ sent_read = false;
+ retries = 0;
+ err = 0;
+
+ if (vsock_vmci_notify_waiting_write(vsk)) {
+ /* Notify the peer that we have read, retrying the send on
+ * failure up to our maximum value. XXX For now we just log
+ * the failure, but later we should schedule a work item to
+ * handle the resend until it succeeds. That would require
+ * keeping track of work items in the vsk and cleaning them up
+ * upon socket close.
+ */
+ while (!(vsk->peer_shutdown & RCV_SHUTDOWN) &&
+ !sent_read && retries < VSOCK_MAX_DGRAM_RESENDS) {
+ err = VSOCK_SEND_READ(sk);
+ if (err >= 0)
+ sent_read = true;
+
+ retries++;
+ }
+
+ if (retries >= VSOCK_MAX_DGRAM_RESENDS && !sent_read)
+ pr_err("%p unable to send read notification to peer\n",
+ sk);
+ else
+ PKT_FIELD(vsk, peer_waiting_write) = false;
+
+ }
+ return err;
+}
+
+static void vsock_vmci_notify_pkt_socket_init(struct sock *sk)
+{
+ struct vsock_vmci_sock *vsk;
+ vsk = vsock_sk(sk);
+
+ PKT_FIELD(vsk, write_notify_window) = PAGE_SIZE;
+ PKT_FIELD(vsk, write_notify_min_window) = PAGE_SIZE;
+ PKT_FIELD(vsk, peer_waiting_write) = false;
+ PKT_FIELD(vsk, peer_waiting_write_detected) = false;
+}
+
+static void vsock_vmci_notify_pkt_socket_destruct(struct sock *sk)
+{
+ struct vsock_vmci_sock *vsk;
+ vsk = vsock_sk(sk);
+
+ PKT_FIELD(vsk, write_notify_window) = PAGE_SIZE;
+ PKT_FIELD(vsk, write_notify_min_window) = PAGE_SIZE;
+ PKT_FIELD(vsk, peer_waiting_write) = false;
+ PKT_FIELD(vsk, peer_waiting_write_detected) = false;
+}
+
+static int
+vsock_vmci_notify_pkt_poll_in(struct sock *sk,
+ size_t target, bool *data_ready_now)
+{
+ struct vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ if (vsock_vmci_stream_has_data(vsk)) {
+ *data_ready_now = true;
+ } else {
+ /* We can't read right now because there is nothing in the
+ * queue. Ask for notifications when there is something to
+ * read.
+ */
+ if (sk->sk_state == SS_CONNECTED)
+ vsock_vmci_block_update_write_window(sk);
+
+ *data_ready_now = false;
+ }
+
+ return 0;
+}
+
+static int
+vsock_vmci_notify_pkt_poll_out(struct sock *sk,
+ size_t target, bool *space_avail_now)
+{
+ s64 produce_q_free_space;
+ struct vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ produce_q_free_space = vsock_vmci_stream_has_space(vsk);
+ if (produce_q_free_space > 0) {
+ *space_avail_now = true;
+ return 0;
+ } else if (produce_q_free_space == 0) {
+ /* This is a connected socket but we can't currently send data.
+ * Nothing else to do.
+ */
+ *space_avail_now = false;
+ }
+
+ return 0;
+}
+
+static int
+vsock_vmci_notify_pkt_recv_init(struct sock *sk,
+ size_t target,
+ struct vsock_vmci_recv_notify_data *data)
+{
+ struct vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ data->consume_head = 0;
+ data->produce_tail = 0;
+ data->notify_on_block = false;
+
+ if (PKT_FIELD(vsk, write_notify_min_window) < target + 1) {
+ PKT_FIELD(vsk, write_notify_min_window) = target + 1;
+ if (PKT_FIELD(vsk, write_notify_window) <
+ PKT_FIELD(vsk, write_notify_min_window)) {
+ /* If the current window is smaller than the new
+ * minimal window size, we need to reevaluate whether
+ * we need to notify the sender. If the number of ready
+ * bytes are smaller than the new window, we need to
+ * send a notification to the sender before we block.
+ */
+
+ PKT_FIELD(vsk, write_notify_window) =
+ PKT_FIELD(vsk, write_notify_min_window);
+ data->notify_on_block = true;
+ }
+ }
+
+ return 0;
+}
+
+static int
+vsock_vmci_notify_pkt_recv_pre_block(struct sock *sk,
+ size_t target,
+ struct vsock_vmci_recv_notify_data *data)
+{
+ int err = 0;
+
+ vsock_vmci_block_update_write_window(sk);
+
+ if (data->notify_on_block) {
+ err = vsock_vmci_send_read_notification(sk);
+ if (err < 0)
+ return err;
+
+ data->notify_on_block = false;
+ }
+
+ return err;
+}
+
+static int
+vsock_vmci_notify_pkt_recv_post_dequeue(struct sock *sk,
+ size_t target,
+ ssize_t copied,
+ bool data_read,
+ struct vsock_vmci_recv_notify_data *data)
+{
+ struct vsock_vmci_sock *vsk;
+ int err;
+ bool was_full = false;
+ u64 free_space;
+
+ vsk = vsock_sk(sk);
+ err = 0;
+
+ if (data_read) {
+ smp_mb();
+
+ free_space = vmci_qpair_consume_free_space(vsk->qpair);
+ was_full = free_space == copied;
+
+ if (was_full)
+ PKT_FIELD(vsk, peer_waiting_write) = true;
+
+ err = vsock_vmci_send_read_notification(sk);
+ if (err < 0)
+ return err;
+
+ /* See the comment in vsock_vmci_notify_pkt_send_post_enqueue */
+ sk->sk_data_ready(sk, 0);
+ }
+
+ return err;
+}
+
+static int
+vsock_vmci_notify_pkt_send_init(struct sock *sk,
+ struct vsock_vmci_send_notify_data *data)
+{
+ data->consume_head = 0;
+ data->produce_tail = 0;
+
+ return 0;
+}
+
+static int
+vsock_vmci_notify_pkt_send_post_enqueue(struct sock *sk,
+ ssize_t written,
+ struct vsock_vmci_send_notify_data *data)
+{
+ int err = 0;
+ struct vsock_vmci_sock *vsk;
+ bool sent_wrote = false;
+ bool was_empty;
+ int retries = 0;
+
+ vsk = vsock_sk(sk);
+
+ smp_mb();
+
+ was_empty = (vmci_qpair_produce_buf_ready(vsk->qpair) == written);
+ if (was_empty) {
+ while (!(vsk->peer_shutdown & RCV_SHUTDOWN) &&
+ !sent_wrote && retries < VSOCK_MAX_DGRAM_RESENDS) {
+ err = VSOCK_SEND_WROTE(sk);
+ if (err >= 0)
+ sent_wrote = true;
+
+ retries++;
+ }
+ }
+
+ if (retries >= VSOCK_MAX_DGRAM_RESENDS && !sent_wrote) {
+ pr_err("%p unable to send wrote notification to peer\n",
+ sk);
+ return err;
+ }
+
+ return err;
+}
+
+static void
+vsock_vmci_notify_pkt_handle_pkt(struct sock *sk,
+ struct vsock_packet *pkt,
+ bool bottom_half,
+ struct sockaddr_vm *dst,
+ struct sockaddr_vm *src, bool *pkt_processed)
+{
+ bool processed = false;
+
+ switch (pkt->type) {
+ case VSOCK_PACKET_TYPE_WROTE:
+ vsock_vmci_handle_wrote(sk, pkt, bottom_half, dst, src);
+ processed = true;
+ break;
+ case VSOCK_PACKET_TYPE_READ:
+ vsock_vmci_handle_read(sk, pkt, bottom_half, dst, src);
+ processed = true;
+ break;
+ }
+
+ if (pkt_processed)
+ *pkt_processed = processed;
+
+}
+
+static void vsock_vmci_notify_pkt_process_request(struct sock *sk)
+{
+ struct vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ PKT_FIELD(vsk, write_notify_window) = vsk->consume_size;
+ if (vsk->consume_size < PKT_FIELD(vsk, write_notify_min_window))
+ PKT_FIELD(vsk, write_notify_min_window) = vsk->consume_size;
+
+}
+
+static void vsock_vmci_notify_pkt_process_negotiate(struct sock *sk)
+{
+ struct vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ PKT_FIELD(vsk, write_notify_window) = vsk->consume_size;
+ if (vsk->consume_size < PKT_FIELD(vsk, write_notify_min_window))
+ PKT_FIELD(vsk, write_notify_min_window) = vsk->consume_size;
+
+}
+
+/* Socket always on control packet based operations. */
+struct vsock_vmci_notify_ops vsock_vmci_notify_pkt_q_state_ops = {
+ vsock_vmci_notify_pkt_socket_init,
+ vsock_vmci_notify_pkt_socket_destruct,
+ vsock_vmci_notify_pkt_poll_in,
+ vsock_vmci_notify_pkt_poll_out,
+ vsock_vmci_notify_pkt_handle_pkt,
+ vsock_vmci_notify_pkt_recv_init,
+ vsock_vmci_notify_pkt_recv_pre_block,
+ NULL, /* recv_pre_dequeue */
+ vsock_vmci_notify_pkt_recv_post_dequeue,
+ vsock_vmci_notify_pkt_send_init,
+ NULL, /* send_pre_block */
+ NULL, /* send_pre_enqueue */
+ vsock_vmci_notify_pkt_send_post_enqueue,
+ vsock_vmci_notify_pkt_process_request,
+ vsock_vmci_notify_pkt_process_negotiate,
+};
new file mode 100644
@@ -0,0 +1,270 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2007-2012 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 _VMCI_SOCKETS_H_
+#define _VMCI_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_VMCI_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_VMCI_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_VMCI_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_VMCI_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_VMCI_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_VMCI_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. The value is platform dependent. On ESX,
+ * Linux and Mac OS, it is a struct timeval. On Windows, it is a DWORD.
+ */
+
+#define SO_VMCI_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_VMCI_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 ((unsigned int)-1)
+
+/* Bind to any available port. Works for the svm_port field of
+ * sockaddr_vm.
+ */
+
+#define VMADDR_PORT_ANY ((unsigned int)-1)
+
+/* Invalid vSockets version. */
+
+#define VMCI_SOCKETS_INVALID_VERSION ((unsigned int)-1)
+
+/* The epoch (first) component of the vSockets version. A single byte
+ * representing the epoch component of the vSockets version.
+ */
+
+#define VMCI_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 VMCI_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 VMCI_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)];
+};
+
+#if defined(linux) && defined(__KERNEL__)
+int vmci_sock_get_local_c_id(void);
+#else
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <unistd.h>
+
+#include <stdio.h>
+
+#define VMCI_SOCKETS_DEFAULT_DEVICE "/dev/vsock"
+#define VMCI_SOCKETS_CLASSIC_ESX_DEVICE "/vmfs/devices/char/vsock/vsock"
+#define VMCI_SOCKETS_VERSION 1972
+#define VMCI_SOCKETS_GET_AF_VALUE 1976
+#define VMCI_SOCKETS_GET_LOCAL_CID 1977
+
+/* Returns the current version of vSockets. The version is a 32-bit unsigned
+ * integer that consist of three components: the epoch, the major version, and
+ * the minor version. Use the VMCI_SOCKETS_VERSION macros to extract the
+ * components.
+ */
+
+static inline unsigned int VMCISock_Version(void)
+{
+ int fd;
+ unsigned int version;
+
+ fd = open(VMCI_SOCKETS_DEFAULT_DEVICE, O_RDWR);
+ if (fd < 0) {
+ fd = open(VMCI_SOCKETS_CLASSIC_ESX_DEVICE, O_RDWR);
+ if (fd < 0)
+ return VMCI_SOCKETS_INVALID_VERSION;
+ }
+
+ if (ioctl(fd, VMCI_SOCKETS_VERSION, &version) < 0)
+ version = VMCI_SOCKETS_INVALID_VERSION;
+
+ close(fd);
+ return version;
+}
+
+/* Returns the value to be used for the VMCI Sockets address family. This
+ * value should be used as the domain argument to socket(2) (when you might
+ * otherwise use AF_INET). For VMCI Socket-specific options, this value
+ * should also be used for the level argument to setsockopt(2) (when you might
+ * otherwise use SOL_TCP).
+ */
+
+static inline int vmci_sock_get_af_value_fd(int *out_fd)
+{
+ int fd;
+ int family;
+
+ fd = open(VMCI_SOCKETS_DEFAULT_DEVICE, O_RDWR);
+ if (fd < 0) {
+ fd = open(VMCI_SOCKETS_CLASSIC_ESX_DEVICE, O_RDWR);
+ if (fd < 0)
+ return -1;
+ }
+
+ if (ioctl(fd, VMCI_SOCKETS_GET_AF_VALUE, &family) < 0)
+ family = -1;
+
+ if (family < 0)
+ close(fd);
+ else if (out_fd)
+ *out_fd = fd;
+
+ return family;
+}
+
+/* Retrieve the address family value for vSockets. Returns the value to be
+ * used for the VMCI Sockets address family. This value should be used as the
+ * domain argument to socket(2) (when you might otherwise use AF_INET). For
+ * VMCI Socket-specific options, this value should also be used for the level
+ * argument to setsockopt(2) (when you might otherwise use SOL_TCP).
+ *
+ * This function leaves its descriptor to the vsock device open so that the
+ * socket implementation knows that the socket family is still in use. This
+ * is done because the address family is registered with the kernel on-demand
+ * and a notification is needed to unregister the address family. Use of this
+ * function is thus discouraged; please use vmci_sock_get_af_value_fd()
+ * instead.
+ */
+
+static inline int vmci_sock_get_af_value(void)
+{
+ return vmci_sock_get_af_value_fd(NULL);
+}
+
+/* Release the file descriptor obtained when retrieving the address family
+ * value. Use this to release the file descriptor obtained by calling
+ * vmci_sock_get_af_value_fd().
+ */
+
+static inline void vmci_sock_release_af_value_fd(int fd)
+{
+ if (fd >= 0)
+ close(fd);
+}
+
+/* Retrieve the current context ID. */
+
+static inline unsigned int vmci_sock_get_local_cid(void)
+{
+ int fd;
+ unsigned int context_id;
+
+ fd = open(VMCI_SOCKETS_DEFAULT_DEVICE, O_RDWR);
+ if (fd < 0) {
+ fd = open(VMCI_SOCKETS_CLASSIC_ESX_DEVICE, O_RDWR);
+ if (fd < 0)
+ return VMADDR_CID_ANY;
+ }
+
+ if (ioctl(fd, VMCI_SOCKETS_GET_LOCAL_CID, &context_id) < 0)
+ context_id = VMADDR_CID_ANY;
+
+ close(fd);
+ return context_id;
+}
+#endif
+
+#endif
new file mode 100644
@@ -0,0 +1,79 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2012 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 _VMCI_SOCKETS_PACKET_H_
+#define _VMCI_SOCKETS_PACKET_H_
+
+#include <linux/vmw_vmci_defs.h>
+#include <linux/vmw_vmci_api.h>
+
+/* If the packet format changes in a release then this should change too. */
+#define VSOCK_PACKET_VERSION 1
+
+/* The resource ID on which control packets are sent. */
+#define VSOCK_PACKET_RID 1
+
+enum vsock_packet_type {
+ VSOCK_PACKET_TYPE_INVALID = 0,
+ VSOCK_PACKET_TYPE_REQUEST,
+ VSOCK_PACKET_TYPE_NEGOTIATE,
+ VSOCK_PACKET_TYPE_OFFER,
+ VSOCK_PACKET_TYPE_ATTACH,
+ VSOCK_PACKET_TYPE_WROTE,
+ VSOCK_PACKET_TYPE_READ,
+ VSOCK_PACKET_TYPE_RST,
+ VSOCK_PACKET_TYPE_SHUTDOWN,
+ VSOCK_PACKET_TYPE_WAITING_WRITE,
+ VSOCK_PACKET_TYPE_WAITING_READ,
+ VSOCK_PACKET_TYPE_REQUEST2,
+ VSOCK_PACKET_TYPE_NEGOTIATE2,
+ VSOCK_PACKET_TYPE_MAX
+};
+
+typedef u16 vsock_proto_version;
+#define VSOCK_PROTO_INVALID 0
+#define VSOCK_PROTO_PKT_ON_NOTIFY (1 << 0)
+
+#define VSOCK_PROTO_ALL_SUPPORTED (VSOCK_PROTO_PKT_ON_NOTIFY)
+
+struct vsock_waiting_info {
+ u64 generation;
+ u64 offset;
+};
+
+/* Control packet type for STREAM sockets. DGRAMs have no control packets nor
+ * special packet header for data packets, they are just raw VMCI DGRAM
+ * messages. For STREAMs, control packets are sent over the control channel
+ * while data is written and read directly from queue pairs with no packet
+ * format.
+ */
+struct vsock_packet {
+ struct vmci_datagram dg;
+ u8 version;
+ u8 type;
+ vsock_proto_version proto;
+
+ u32 src_port;
+ u32 dst_port;
+ u32 _reserved2;
+ union {
+ u64 size;
+ u64 mode;
+ struct vmci_handle handle;
+ struct vsock_waiting_info wait;
+ } u;
+};
+
+#endif
new file mode 100644
@@ -0,0 +1,103 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2007-2012 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 _VSOCK_COMMON_H_
+#define _VSOCK_COMMON_H_
+
+/* vmci_sock_get_af_value_int is defined separately from vmci_sock_get_af_value
+ * because it is used in several different contexts. In particular it is called
+ * from vsock_addr.c which gets compiled into both our kernel modules as well
+ * as the user level vsock library. In the linux kernel we need different
+ * behavior than external kernel modules using VMCI Sockets api inside the
+ * kernel. FIXME
+ */
+
+#if defined __KERNEL__
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <asm/page.h>
+#else
+/* In userland, just use the normal exported userlevel api. */
+#define vmci_sock_get_af_value_int() vmci_sock_get_af_value()
+#endif
+
+#include <linux/vmw_vmci_defs.h>
+#include <linux/vmw_vmci_api.h>
+
+#include "vmci_sockets.h"
+#include "vsock_addr.h"
+
+#ifdef __x86_64__
+#define FMT64 "ll"
+#else
+#define FMT64 "L"
+#endif
+
+#define MAX_UINT32 ((u32)0xffffffff)
+
+#ifndef ESYSNOTREADY
+#define ESYSNOTREADY EOPNOTSUPP
+#endif
+
+#define sockerr() errno
+#define sockerr2err(_e) (((_e) > 0) ? -(_e) : (_e))
+#define SS_LISTEN 255
+
+extern u32 vmci_get_context_id(void);
+
+/* Helper function to determine if the given handle points to the local context.
+ * Returns TRUE if the given handle is for the local context, FALSE otherwise.
+ */
+
+static inline bool vsock_vmci_is_local(struct vmci_handle handle)
+{
+ return vmci_get_context_id() == handle.context;
+}
+
+/* Helper function to convert from a VMCI error code to a VSock error code. */
+
+static inline s32 vsock_vmci_error_to_vsock_error(s32 vmci_error)
+{
+ int err;
+
+ switch (vmci_error) {
+ case VMCI_ERROR_NO_MEM:
+ err = ENOMEM;
+ break;
+ case VMCI_ERROR_DUPLICATE_ENTRY:
+ case VMCI_ERROR_ALREADY_EXISTS:
+ err = EADDRINUSE;
+ break;
+ case VMCI_ERROR_NO_ACCESS:
+ err = EPERM;
+ break;
+ case VMCI_ERROR_NO_RESOURCES:
+ err = ENOBUFS;
+ break;
+ case VMCI_ERROR_INVALID_RESOURCE:
+ err = EHOSTUNREACH;
+ break;
+ case VMCI_ERROR_MODULE_NOT_LOADED:
+ err = ESYSNOTREADY;
+ break;
+ case VMCI_ERROR_INVALID_ARGS:
+ default:
+ err = EINVAL;
+ }
+
+ return sockerr2err(err);
+}
+
+#endif
new file mode 100644
@@ -0,0 +1,92 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2007-2012 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 _VSOCK_PACKET_H_
+#define _VSOCK_PACKET_H_
+
+#include "vmci_sockets_packet.h"
+
+static inline void
+vsock_packet_init(struct vsock_packet *pkt,
+ struct sockaddr_vm *src,
+ struct sockaddr_vm *dst,
+ u8 type,
+ u64 size,
+ u64 mode,
+ struct vsock_waiting_info *wait,
+ vsock_proto_version proto,
+ struct vmci_handle handle)
+{
+ /* We register the stream control handler as an any cid handle so we
+ * must always send from a source address of VMADDR_CID_ANY
+ */
+ pkt->dg.src = vmci_make_handle(VMADDR_CID_ANY, VSOCK_PACKET_RID);
+ pkt->dg.dst = vmci_make_handle(dst->svm_cid, VSOCK_PACKET_RID);
+ pkt->dg.payload_size = sizeof(*pkt) - sizeof(pkt->dg);
+ pkt->version = VSOCK_PACKET_VERSION;
+ pkt->type = type;
+ pkt->src_port = src->svm_port;
+ pkt->dst_port = dst->svm_port;
+ memset(&pkt->proto, 0, sizeof(pkt->proto));
+ memset(&pkt->_reserved2, 0, sizeof(pkt->_reserved2));
+
+ switch (pkt->type) {
+ case VSOCK_PACKET_TYPE_INVALID:
+ pkt->u.size = 0;
+ break;
+
+ case VSOCK_PACKET_TYPE_REQUEST:
+ case VSOCK_PACKET_TYPE_NEGOTIATE:
+ pkt->u.size = size;
+ break;
+
+ case VSOCK_PACKET_TYPE_OFFER:
+ case VSOCK_PACKET_TYPE_ATTACH:
+ pkt->u.handle = handle;
+ break;
+
+ case VSOCK_PACKET_TYPE_WROTE:
+ case VSOCK_PACKET_TYPE_READ:
+ case VSOCK_PACKET_TYPE_RST:
+ pkt->u.size = 0;
+ break;
+
+ case VSOCK_PACKET_TYPE_SHUTDOWN:
+ pkt->u.mode = mode;
+ break;
+
+ case VSOCK_PACKET_TYPE_WAITING_READ:
+ case VSOCK_PACKET_TYPE_WAITING_WRITE:
+ memcpy(&pkt->u.wait, wait, sizeof(pkt->u.wait));
+ break;
+
+ case VSOCK_PACKET_TYPE_REQUEST2:
+ case VSOCK_PACKET_TYPE_NEGOTIATE2:
+ pkt->u.size = size;
+ pkt->proto = proto;
+ break;
+ }
+}
+
+static inline void
+vsock_packet_get_addresses(struct vsock_packet *pkt,
+ struct sockaddr_vm *local,
+ struct sockaddr_vm *remote)
+{
+ vsock_addr_init(local, pkt->dg.dst.context, pkt->dst_port);
+ vsock_addr_init(remote, pkt->dg.src.context, pkt->src_port);
+}
+
+#endif
new file mode 100644
@@ -0,0 +1,22 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2011-2012 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 _VSOCK_VERSION_H_
+#define _VSOCK_VERSION_H_
+
+#define VSOCK_DRIVER_VERSION_PARTS { 1, 0, 0, 0 }
+#define VSOCK_DRIVER_VERSION_STRING "1.0.0.0-k"
+
+#endif /* _VSOCK_VERSION_H_ */