[dpdk-dev] [PATCH v3 09/11] lib/librte_vhost: vhost user support

[Przemyslaw Czesnowicz <przemyslaw.czesnowicz@intel.com>]

From: "Xie, Huawei" <huawei.xie@intel.com>

In rte_vhost_driver_register(), vhost unix domain socket listener fd is created
and added to polled(based on select) fdset.

In rte_vhost_driver_session_start(), fds in the fdset are checked for
processing. If there is new connection from qemu, connection fd accepted is
added to polled fdset. The listener and connection fds in the fdset are
then both checked. When there is message on the connection fd, its
callback vserver_message_handler is called to process vhost-user messages.

To support identifying which virtio is from which guest VM, we could call
rte_vhost_driver_register with different socket path. Virtio devices from
same VM will connect to VM specific socket. The socket path information is
stored in the virtio_net structure.

Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Signed-off-by: Przemyslaw Czesnowicz <przemyslaw.czesnowicz@intel.com>
---
 lib/librte_vhost/Makefile                     |   8 +-
 lib/librte_vhost/rte_virtio_net.h             |   2 +
 lib/librte_vhost/vhost-net.h                  |   4 +-
 lib/librte_vhost/vhost_user/vhost-net-user.c  | 457 ++++++++++++++++++++++++++
 lib/librte_vhost/vhost_user/vhost-net-user.h  | 106 ++++++
 lib/librte_vhost/vhost_user/virtio-net-user.c | 314 ++++++++++++++++++
 lib/librte_vhost/vhost_user/virtio-net-user.h |  49 +++
 lib/librte_vhost/virtio-net.c                 |  15 +-
 8 files changed, 948 insertions(+), 7 deletions(-)
 create mode 100644 lib/librte_vhost/vhost_user/vhost-net-user.c
 create mode 100644 lib/librte_vhost/vhost_user/vhost-net-user.h
 create mode 100644 lib/librte_vhost/vhost_user/virtio-net-user.c
 create mode 100644 lib/librte_vhost/vhost_user/virtio-net-user.h

diff --git a/lib/librte_vhost/Makefile b/lib/librte_vhost/Makefile
index 298e4f8..cac943e 100644
--- a/lib/librte_vhost/Makefile
+++ b/lib/librte_vhost/Makefile
@@ -38,10 +38,14 @@ EXPORT_MAP := rte_vhost_version.map
 
 LIBABIVER := 1
 
-CFLAGS += $(WERROR_FLAGS) -I$(SRCDIR) -I vhost_cuse -O3 -D_FILE_OFFSET_BITS=64 -lfuse
+CFLAGS += $(WERROR_FLAGS) -I$(SRCDIR) -O3 -D_FILE_OFFSET_BITS=64
+CFLAGS += -I vhost_cuse -lfuse
+CFLAGS += -I vhost_user
 LDFLAGS += -lfuse
 # all source are stored in SRCS-y
-SRCS-$(CONFIG_RTE_LIBRTE_VHOST) := virtio-net.c vhost_cuse/vhost-net-cdev.c vhost_cuse/virtio-net-cdev.c vhost_cuse/eventfd_copy.c vhost_rxtx.c
+SRCS-$(CONFIG_RTE_LIBRTE_VHOST) := virtio-net.c vhost_rxtx.c vhost_cuse/eventfd_copy.c
+#SRCS-$(CONFIG_RTE_LIBRTE_VHOST) += vhost_cuse/vhost-net-cdev.c vhost_cuse/virtio-net-cdev.c vhost_cuse/eventfd_copy.c
+SRCS-$(CONFIG_RTE_LIBRTE_VHOST) += vhost_user/vhost-net-user.c vhost_user/virtio-net-user.c vhost_user/fd_man.c
 
 # install includes
 SYMLINK-$(CONFIG_RTE_LIBRTE_VHOST)-include += rte_virtio_net.h
diff --git a/lib/librte_vhost/rte_virtio_net.h b/lib/librte_vhost/rte_virtio_net.h
index 0bf07c7..46c2072 100644
--- a/lib/librte_vhost/rte_virtio_net.h
+++ b/lib/librte_vhost/rte_virtio_net.h
@@ -50,6 +50,8 @@
 #include <rte_mempool.h>
 #include <rte_mbuf.h>
 
+#define VHOST_MEMORY_MAX_NREGIONS 8
+
 /* Used to indicate that the device is running on a data core */
 #define VIRTIO_DEV_RUNNING 1
 
diff --git a/lib/librte_vhost/vhost-net.h b/lib/librte_vhost/vhost-net.h
index 86b38a5..a56e405 100644
--- a/lib/librte_vhost/vhost-net.h
+++ b/lib/librte_vhost/vhost-net.h
@@ -41,7 +41,9 @@
 
 #include <rte_log.h>
 
-#define VHOST_MEMORY_MAX_NREGIONS 8
+#include "rte_virtio_net.h"
+
+extern struct vhost_net_device_ops const *ops;
 
 /* Macros for printing using RTE_LOG */
 #define RTE_LOGTYPE_VHOST_CONFIG RTE_LOGTYPE_USER1
diff --git a/lib/librte_vhost/vhost_user/vhost-net-user.c b/lib/librte_vhost/vhost_user/vhost-net-user.c
new file mode 100644
index 0000000..712a82f
--- /dev/null
+++ b/lib/librte_vhost/vhost_user/vhost-net-user.c
@@ -0,0 +1,457 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * 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.
+ *     * Neither the name of Intel Corporation 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 THE COPYRIGHT
+ *   OWNER 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.
+ */
+
+#include <stdint.h>
+#include <stdio.h>
+#include <limits.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <errno.h>
+
+#include <rte_log.h>
+#include <rte_virtio_net.h>
+
+#include "fd_man.h"
+#include "vhost-net-user.h"
+#include "vhost-net.h"
+#include "virtio-net-user.h"
+
+#define MAX_VIRTIO_BACKLOG 128
+static void vserver_new_vq_conn(int fd, void *data);
+static void vserver_message_handler(int fd, void *dat);
+struct vhost_net_device_ops const *ops;
+
+struct connfd_ctx {
+	struct vhost_server *vserver;
+	uint32_t fh;
+};
+
+#define MAX_VHOST_SERVER 1024
+static struct {
+	struct vhost_server *server[MAX_VHOST_SERVER];
+	struct fdset fdset;	/**< The fd list this vhost server manages. */
+} g_vhost_server;
+
+static int vserver_idx;
+
+static const char *vhost_message_str[VHOST_USER_MAX] = {
+	[VHOST_USER_NONE] = "VHOST_USER_NONE",
+	[VHOST_USER_GET_FEATURES] = "VHOST_USER_GET_FEATURES",
+	[VHOST_USER_SET_FEATURES] = "VHOST_USER_SET_FEATURES",
+	[VHOST_USER_SET_OWNER] = "VHOST_USER_SET_OWNER",
+	[VHOST_USER_RESET_OWNER] = "VHOST_USER_RESET_OWNER",
+	[VHOST_USER_SET_MEM_TABLE] = "VHOST_USER_SET_MEM_TABLE",
+	[VHOST_USER_SET_LOG_BASE] = "VHOST_USER_SET_LOG_BASE",
+	[VHOST_USER_SET_LOG_FD] = "VHOST_USER_SET_LOG_FD",
+	[VHOST_USER_SET_VRING_NUM] = "VHOST_USER_SET_VRING_NUM",
+	[VHOST_USER_SET_VRING_ADDR] = "VHOST_USER_SET_VRING_ADDR",
+	[VHOST_USER_SET_VRING_BASE] = "VHOST_USER_SET_VRING_BASE",
+	[VHOST_USER_GET_VRING_BASE] = "VHOST_USER_GET_VRING_BASE",
+	[VHOST_USER_SET_VRING_KICK] = "VHOST_USER_SET_VRING_KICK",
+	[VHOST_USER_SET_VRING_CALL] = "VHOST_USER_SET_VRING_CALL",
+	[VHOST_USER_SET_VRING_ERR]  = "VHOST_USER_SET_VRING_ERR"
+};
+
+/**
+ * Create a unix domain socket, bind to path and listen for connection.
+ * @return
+ *  socket fd or -1 on failure
+ */
+static int
+uds_socket(const char *path)
+{
+	struct sockaddr_un un;
+	int sockfd;
+	int ret;
+
+	if (path == NULL)
+		return -1;
+
+	sockfd = socket(AF_UNIX, SOCK_STREAM, 0);
+	if (sockfd < 0)
+		return -1;
+	RTE_LOG(INFO, VHOST_CONFIG, "socket created, fd:%d\n", sockfd);
+
+	memset(&un, 0, sizeof(un));
+	un.sun_family = AF_UNIX;
+	snprintf(un.sun_path, sizeof(un.sun_path), "%s", path);
+	ret = bind(sockfd, (struct sockaddr *)&un, sizeof(un));
+	if (ret == -1)
+		goto err;
+	RTE_LOG(INFO, VHOST_CONFIG, "bind to %s\n", path);
+
+	ret = listen(sockfd, MAX_VIRTIO_BACKLOG);
+	if (ret == -1)
+		goto err;
+
+	return sockfd;
+
+err:
+	close(sockfd);
+	return -1;
+}
+
+/* return bytes# of read on success or negative val on failure. */
+static int
+read_fd_message(int sockfd, char *buf, int buflen, int *fds, int fd_num)
+{
+	struct iovec iov;
+	struct msghdr msgh;
+	size_t fdsize = fd_num * sizeof(int);
+	char control[CMSG_SPACE(fdsize)];
+	struct cmsghdr *cmsg;
+	int ret;
+
+	memset(&msgh, 0, sizeof(msgh));
+	iov.iov_base = buf;
+	iov.iov_len  = buflen;
+
+	msgh.msg_iov = &iov;
+	msgh.msg_iovlen = 1;
+	msgh.msg_control = control;
+	msgh.msg_controllen = sizeof(control);
+
+	ret = recvmsg(sockfd, &msgh, 0);
+	if (ret <= 0) {
+		RTE_LOG(ERR, VHOST_CONFIG, "recvmsg failed\n");
+		return ret;
+	}
+
+	if (msgh.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) {
+		RTE_LOG(ERR, VHOST_CONFIG, "truncted msg\n");
+		return -1;
+	}
+
+	for (cmsg = CMSG_FIRSTHDR(&msgh); cmsg != NULL;
+		cmsg = CMSG_NXTHDR(&msgh, cmsg)) {
+		if ((cmsg->cmsg_level == SOL_SOCKET) &&
+			(cmsg->cmsg_type == SCM_RIGHTS)) {
+			memcpy(fds, CMSG_DATA(cmsg), fdsize);
+			break;
+		}
+	}
+
+	return ret;
+}
+
+/* return bytes# of read on success or negative val on failure. */
+static int
+read_vhost_message(int sockfd, struct VhostUserMsg *msg)
+{
+	int ret;
+
+	ret = read_fd_message(sockfd, (char *)msg, VHOST_USER_HDR_SIZE,
+		msg->fds, VHOST_MEMORY_MAX_NREGIONS);
+	if (ret <= 0)
+		return ret;
+
+	if (msg && msg->size) {
+		if (msg->size > sizeof(msg->payload)) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"invalid msg size: %d\n", msg->size);
+			return -1;
+		}
+		ret = read(sockfd, &msg->payload, msg->size);
+		if (ret <= 0)
+			return ret;
+		if (ret != (int)msg->size) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"read control message failed\n");
+			return -1;
+		}
+	}
+
+	return ret;
+}
+
+static int
+send_fd_message(int sockfd, char *buf, int buflen, int *fds, int fd_num)
+{
+
+	struct iovec iov;
+	struct msghdr msgh;
+	size_t fdsize = fd_num * sizeof(int);
+	char control[CMSG_SPACE(fdsize)];
+	struct cmsghdr *cmsg;
+	int ret;
+
+	memset(&msgh, 0, sizeof(msgh));
+	iov.iov_base = buf;
+	iov.iov_len = buflen;
+
+	msgh.msg_iov = &iov;
+	msgh.msg_iovlen = 1;
+
+	if (fds && fd_num > 0) {
+		msgh.msg_control = control;
+		msgh.msg_controllen = sizeof(control);
+		cmsg = CMSG_FIRSTHDR(&msgh);
+		cmsg->cmsg_len = CMSG_LEN(fdsize);
+		cmsg->cmsg_level = SOL_SOCKET;
+		cmsg->cmsg_type = SCM_RIGHTS;
+		memcpy(CMSG_DATA(cmsg), fds, fdsize);
+	} else {
+		msgh.msg_control = NULL;
+		msgh.msg_controllen = 0;
+	}
+
+	do {
+		ret = sendmsg(sockfd, &msgh, 0);
+	} while (ret < 0 && errno == EINTR);
+
+	if (ret < 0) {
+		RTE_LOG(ERR, VHOST_CONFIG,  "sendmsg error\n");
+		return ret;
+	}
+
+	return ret;
+}
+
+static int
+send_vhost_message(int sockfd, struct VhostUserMsg *msg)
+{
+	int ret;
+
+	if (!msg)
+		return 0;
+
+	msg->flags &= ~VHOST_USER_VERSION_MASK;
+	msg->flags |= VHOST_USER_VERSION;
+	msg->flags |= VHOST_USER_REPLY_MASK;
+
+	ret = send_fd_message(sockfd, (char *)msg,
+		VHOST_USER_HDR_SIZE + msg->size, NULL, 0);
+
+	return ret;
+}
+
+/* call back when there is new virtio connection.  */
+static void
+vserver_new_vq_conn(int fd, void *dat)
+{
+	struct vhost_server *vserver = (struct vhost_server *)dat;
+	int conn_fd;
+	struct connfd_ctx *ctx;
+	int fh;
+	struct vhost_device_ctx vdev_ctx = { 0 };
+
+	conn_fd = accept(fd, NULL, NULL);
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"new virtio connection is %d\n", conn_fd);
+	if (conn_fd < 0)
+		return;
+
+	ctx = calloc(1, sizeof(*ctx));
+	if (ctx == NULL) {
+		close(conn_fd);
+		return;
+	}
+
+	fh = ops->new_device(vdev_ctx);
+	if (fh == -1) {
+		free(ctx);
+		close(conn_fd);
+		return;
+	}
+	RTE_LOG(INFO, VHOST_CONFIG, "new device, handle is %d\n", fh);
+
+	ctx->vserver = vserver;
+	ctx->fh = fh;
+	fdset_add(&g_vhost_server.fdset,
+		conn_fd, vserver_message_handler, NULL, ctx);
+}
+
+/* callback when there is message on the connfd */
+static void
+vserver_message_handler(int connfd, void *dat)
+{
+	struct vhost_device_ctx ctx;
+	struct connfd_ctx *cfd_ctx = (struct connfd_ctx *)dat;
+	struct VhostUserMsg msg;
+	uint64_t features;
+	int ret;
+
+	ctx.fh = cfd_ctx->fh;
+	ret = read_vhost_message(connfd, &msg);
+	if (ret < 0) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"vhost read message failed\n");
+
+		close(connfd);
+		fdset_del(&g_vhost_server.fdset, connfd);
+		free(cfd_ctx);
+		user_destroy_device(ctx);
+		ops->destroy_device(ctx);
+
+		return;
+	} else if (ret == 0) {
+		RTE_LOG(INFO, VHOST_CONFIG,
+			"vhost peer closed\n");
+
+		close(connfd);
+		fdset_del(&g_vhost_server.fdset, connfd);
+		free(cfd_ctx);
+		user_destroy_device(ctx);
+		ops->destroy_device(ctx);
+
+		return;
+	}
+	if (msg.request > VHOST_USER_MAX) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"vhost read incorrect message\n");
+
+		close(connfd);
+		fdset_del(&g_vhost_server.fdset, connfd);
+		free(cfd_ctx);
+		user_destroy_device(ctx);
+		ops->destroy_device(ctx);
+
+		return;
+	}
+
+	RTE_LOG(INFO, VHOST_CONFIG, "read message %s\n",
+		vhost_message_str[msg.request]);
+	switch (msg.request) {
+	case VHOST_USER_GET_FEATURES:
+		ret = ops->get_features(ctx, &features);
+		msg.payload.u64 = features;
+		msg.size = sizeof(msg.payload.u64);
+		send_vhost_message(connfd, &msg);
+		break;
+	case VHOST_USER_SET_FEATURES:
+		features = msg.payload.u64;
+		ops->set_features(ctx, &features);
+		break;
+
+	case VHOST_USER_SET_OWNER:
+		ops->set_owner(ctx);
+		break;
+	case VHOST_USER_RESET_OWNER:
+		ops->reset_owner(ctx);
+		break;
+
+	case VHOST_USER_SET_MEM_TABLE:
+		user_set_mem_table(ctx, &msg);
+		break;
+
+	case VHOST_USER_SET_LOG_BASE:
+		RTE_LOG(INFO, VHOST_CONFIG, "not implemented.\n");
+	case VHOST_USER_SET_LOG_FD:
+		close(msg.fds[0]);
+		RTE_LOG(INFO, VHOST_CONFIG, "not implemented.\n");
+		break;
+
+	case VHOST_USER_SET_VRING_NUM:
+		ops->set_vring_num(ctx, &msg.payload.state);
+		break;
+	case VHOST_USER_SET_VRING_ADDR:
+		ops->set_vring_addr(ctx, &msg.payload.addr);
+		break;
+	case VHOST_USER_SET_VRING_BASE:
+		ops->set_vring_base(ctx, &msg.payload.state);
+		break;
+
+	case VHOST_USER_GET_VRING_BASE:
+		ret = user_get_vring_base(ctx, &msg.payload.state);
+		msg.size = sizeof(msg.payload.state);
+		send_vhost_message(connfd, &msg);
+		break;
+
+	case VHOST_USER_SET_VRING_KICK:
+		user_set_vring_kick(ctx, &msg);
+		break;
+	case VHOST_USER_SET_VRING_CALL:
+		user_set_vring_call(ctx, &msg);
+		break;
+
+	case VHOST_USER_SET_VRING_ERR:
+		if (!(msg.payload.u64 & VHOST_USER_VRING_NOFD_MASK))
+			close(msg.fds[0]);
+		RTE_LOG(INFO, VHOST_CONFIG, "not implemented\n");
+		break;
+
+	default:
+		break;
+
+	}
+}
+
+
+/**
+ * Creates and initialise the vhost server.
+ */
+int
+rte_vhost_driver_register(const char *path)
+{
+	struct vhost_server *vserver;
+
+	if (vserver_idx == 0) {
+		fdset_init(&g_vhost_server.fdset);
+		ops = get_virtio_net_callbacks();
+	}
+	if (vserver_idx == MAX_VHOST_SERVER)
+		return -1;
+
+	vserver = calloc(sizeof(struct vhost_server), 1);
+	if (vserver == NULL)
+		return -1;
+
+	unlink(path);
+
+	vserver->listenfd = uds_socket(path);
+	if (vserver->listenfd < 0) {
+		free(vserver);
+		return -1;
+	}
+	vserver->path = path;
+
+	fdset_add(&g_vhost_server.fdset, vserver->listenfd,
+		vserver_new_vq_conn, NULL,
+		vserver);
+
+	g_vhost_server.server[vserver_idx++] = vserver;
+
+	return 0;
+}
+
+
+int
+rte_vhost_driver_session_start(void)
+{
+	fdset_event_dispatch(&g_vhost_server.fdset);
+	return 0;
+}
diff --git a/lib/librte_vhost/vhost_user/vhost-net-user.h b/lib/librte_vhost/vhost_user/vhost-net-user.h
new file mode 100644
index 0000000..1b6be6c
--- /dev/null
+++ b/lib/librte_vhost/vhost_user/vhost-net-user.h
@@ -0,0 +1,106 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * 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.
+ *     * Neither the name of Intel Corporation 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 THE COPYRIGHT
+ *   OWNER 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.
+ */
+
+#ifndef _VHOST_NET_USER_H
+#define _VHOST_NET_USER_H
+
+#include <stdint.h>
+#include <linux/vhost.h>
+
+#include "rte_virtio_net.h"
+#include "fd_man.h"
+
+struct vhost_server {
+	const char *path; /**< The path the uds is bind to. */
+	int listenfd;     /**< The listener sockfd. */
+};
+
+/* refer to hw/virtio/vhost-user.c */
+
+typedef enum VhostUserRequest {
+	VHOST_USER_NONE = 0,
+	VHOST_USER_GET_FEATURES = 1,
+	VHOST_USER_SET_FEATURES = 2,
+	VHOST_USER_SET_OWNER = 3,
+	VHOST_USER_RESET_OWNER = 4,
+	VHOST_USER_SET_MEM_TABLE = 5,
+	VHOST_USER_SET_LOG_BASE = 6,
+	VHOST_USER_SET_LOG_FD = 7,
+	VHOST_USER_SET_VRING_NUM = 8,
+	VHOST_USER_SET_VRING_ADDR = 9,
+	VHOST_USER_SET_VRING_BASE = 10,
+	VHOST_USER_GET_VRING_BASE = 11,
+	VHOST_USER_SET_VRING_KICK = 12,
+	VHOST_USER_SET_VRING_CALL = 13,
+	VHOST_USER_SET_VRING_ERR = 14,
+	VHOST_USER_MAX
+} VhostUserRequest;
+
+typedef struct VhostUserMemoryRegion {
+	uint64_t guest_phys_addr;
+	uint64_t memory_size;
+	uint64_t userspace_addr;
+	uint64_t mmap_offset;
+} VhostUserMemoryRegion;
+
+typedef struct VhostUserMemory {
+	uint32_t nregions;
+	uint32_t padding;
+	VhostUserMemoryRegion regions[VHOST_MEMORY_MAX_NREGIONS];
+} VhostUserMemory;
+
+typedef struct VhostUserMsg {
+	VhostUserRequest request;
+
+#define VHOST_USER_VERSION_MASK     0x3
+#define VHOST_USER_REPLY_MASK       (0x1 << 2)
+	uint32_t flags;
+	uint32_t size; /* the following payload size */
+	union {
+#define VHOST_USER_VRING_IDX_MASK   0xff
+#define VHOST_USER_VRING_NOFD_MASK  (0x1<<8)
+		uint64_t u64;
+		struct vhost_vring_state state;
+		struct vhost_vring_addr addr;
+		VhostUserMemory memory;
+	} payload;
+	int fds[VHOST_MEMORY_MAX_NREGIONS];
+} __attribute((packed)) VhostUserMsg;
+
+#define VHOST_USER_HDR_SIZE offsetof(VhostUserMsg, payload.u64)
+
+/* The version of the protocol we support */
+#define VHOST_USER_VERSION    0x1
+
+/*****************************************************************************/
+#endif
diff --git a/lib/librte_vhost/vhost_user/virtio-net-user.c b/lib/librte_vhost/vhost_user/virtio-net-user.c
new file mode 100644
index 0000000..97c5177
--- /dev/null
+++ b/lib/librte_vhost/vhost_user/virtio-net-user.c
@@ -0,0 +1,314 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * 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.
+ *     * Neither the name of Intel Corporation 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 THE COPYRIGHT
+ *   OWNER 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.
+ */
+
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include <rte_common.h>
+#include <rte_log.h>
+
+#include "virtio-net.h"
+#include "virtio-net-user.h"
+#include "vhost-net-user.h"
+#include "vhost-net.h"
+
+struct orig_region_map {
+	int fd;
+	uint64_t mapped_address;
+	uint64_t mapped_size;
+	uint64_t blksz;
+};
+
+#define orig_region(ptr, nregions) \
+	((struct orig_region_map *)RTE_PTR_ADD((ptr), \
+		sizeof(struct virtio_memory) + \
+		sizeof(struct virtio_memory_regions) * (nregions)))
+
+static uint64_t
+get_blk_size(int fd)
+{
+	struct stat stat;
+
+	fstat(fd, &stat);
+	return (uint64_t)stat.st_blksize;
+}
+
+static void
+free_mem_region(struct virtio_net *dev)
+{
+	struct orig_region_map *region;
+	unsigned int idx;
+	uint64_t alignment;
+
+	if (!dev || !dev->mem)
+		return;
+
+	region = orig_region(dev->mem, dev->mem->nregions);
+	for (idx = 0; idx < dev->mem->nregions; idx++) {
+		if (region[idx].mapped_address) {
+			alignment = region[idx].blksz;
+			munmap((void *)
+				RTE_ALIGN_FLOOR(
+					region[idx].mapped_address, alignment),
+				RTE_ALIGN_CEIL(
+					region[idx].mapped_size, alignment));
+			close(region[idx].fd);
+		}
+	}
+}
+
+int
+user_set_mem_table(struct vhost_device_ctx ctx, struct VhostUserMsg *pmsg)
+{
+	struct VhostUserMemory memory = pmsg->payload.memory;
+	struct virtio_memory_regions *pregion;
+	uint64_t mapped_address, mapped_size;
+	struct virtio_net *dev;
+	unsigned int idx = 0;
+	struct orig_region_map *pregion_orig;
+	uint64_t alignment;
+
+	/* unmap old memory regions one by one*/
+	dev = get_device(ctx);
+	if (dev == NULL)
+		return -1;
+
+	if (dev->mem) {
+		free_mem_region(dev);
+		free(dev->mem);
+		dev->mem = NULL;
+	}
+
+	dev->mem = calloc(1,
+		sizeof(struct virtio_memory) +
+		sizeof(struct virtio_memory_regions) * memory.nregions +
+		sizeof(struct orig_region_map) * memory.nregions);
+	if (dev->mem == NULL) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"(%"PRIu64") Failed to allocate memory for dev->mem\n",
+			dev->device_fh);
+		return -1;
+	}
+	dev->mem->nregions = memory.nregions;
+
+	pregion_orig = orig_region(dev->mem, memory.nregions);
+	for (idx = 0; idx < memory.nregions; idx++) {
+		pregion = &dev->mem->regions[idx];
+		pregion->guest_phys_address =
+			memory.regions[idx].guest_phys_addr;
+		pregion->guest_phys_address_end =
+			memory.regions[idx].guest_phys_addr +
+			memory.regions[idx].memory_size;
+		pregion->memory_size =
+			memory.regions[idx].memory_size;
+		pregion->userspace_address =
+			memory.regions[idx].userspace_addr;
+
+		/* This is ugly */
+		mapped_size = memory.regions[idx].memory_size +
+			memory.regions[idx].mmap_offset;
+		mapped_address = (uint64_t)(uintptr_t)mmap(NULL,
+			mapped_size,
+			PROT_READ | PROT_WRITE, MAP_SHARED,
+			pmsg->fds[idx],
+			0);
+
+		RTE_LOG(INFO, VHOST_CONFIG,
+			"mapped region %d fd:%d to %p sz:0x%"PRIx64" off:0x%"PRIx64"\n",
+			idx, pmsg->fds[idx], (void *)mapped_address,
+			mapped_size, memory.regions[idx].mmap_offset);
+
+		if (mapped_address == (uint64_t)(uintptr_t)MAP_FAILED) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"mmap qemu guest failed.\n");
+			goto err_mmap;
+		}
+
+		pregion_orig[idx].mapped_address = mapped_address;
+		pregion_orig[idx].mapped_size = mapped_size;
+		pregion_orig[idx].blksz = get_blk_size(pmsg->fds[idx]);
+		pregion_orig[idx].fd = pmsg->fds[idx];
+
+		mapped_address +=  memory.regions[idx].mmap_offset;
+
+		pregion->address_offset = mapped_address -
+			pregion->guest_phys_address;
+
+		if (memory.regions[idx].guest_phys_addr == 0) {
+			dev->mem->base_address =
+				memory.regions[idx].userspace_addr;
+			dev->mem->mapped_address =
+				pregion->address_offset;
+		}
+
+		LOG_DEBUG(VHOST_CONFIG,
+			"REGION: %u GPA: %p QEMU VA: %p SIZE (%"PRIu64")\n",
+			idx,
+			(void *)(uintptr_t)pregion->guest_phys_address,
+			(void *)(uintptr_t)pregion->userspace_address,
+			 pregion->memory_size);
+	}
+
+	return 0;
+
+err_mmap:
+	while (idx--) {
+		alignment = pregion_orig[idx].blksz;
+		munmap((void *)RTE_ALIGN_FLOOR(
+			pregion_orig[idx].mapped_address, alignment),
+			RTE_ALIGN_CEIL(pregion_orig[idx].mapped_size,
+					alignment));
+		close(pregion_orig[idx].fd);
+	}
+	free(dev->mem);
+	dev->mem = NULL;
+	return -1;
+}
+
+static int
+virtio_is_ready(struct virtio_net *dev)
+{
+	struct vhost_virtqueue *rvq, *tvq;
+
+	/* mq support in future.*/
+	rvq = dev->virtqueue[VIRTIO_RXQ];
+	tvq = dev->virtqueue[VIRTIO_TXQ];
+	if (rvq && tvq && rvq->desc && tvq->desc &&
+		(rvq->kickfd != (eventfd_t)-1) &&
+		(rvq->callfd != (eventfd_t)-1) &&
+		(tvq->kickfd != (eventfd_t)-1) &&
+		(tvq->callfd != (eventfd_t)-1)) {
+		RTE_LOG(INFO, VHOST_CONFIG,
+			"virtio is now ready for processing.\n");
+		return 1;
+	}
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"virtio isn't ready for processing.\n");
+	return 0;
+}
+
+void
+user_set_vring_call(struct vhost_device_ctx ctx, struct VhostUserMsg *pmsg)
+{
+	struct vhost_vring_file file;
+
+	file.index = pmsg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
+	if (pmsg->payload.u64 & VHOST_USER_VRING_NOFD_MASK)
+		file.fd = -1;
+	else
+		file.fd = pmsg->fds[0];
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"vring call idx:%d file:%d\n", file.index, file.fd);
+	ops->set_vring_call(ctx, &file);
+}
+
+
+/*
+ *  In vhost-user, when we receive kick message, will test whether virtio
+ *  device is ready for packet processing.
+ */
+void
+user_set_vring_kick(struct vhost_device_ctx ctx, struct VhostUserMsg *pmsg)
+{
+	struct vhost_vring_file file;
+	struct virtio_net *dev = get_device(ctx);
+
+	file.index = pmsg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
+	if (pmsg->payload.u64 & VHOST_USER_VRING_NOFD_MASK)
+		file.fd = -1;
+	else
+		file.fd = pmsg->fds[0];
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"vring kick idx:%d file:%d\n", file.index, file.fd);
+	ops->set_vring_kick(ctx, &file);
+
+	if (virtio_is_ready(dev) &&
+		!(dev->flags & VIRTIO_DEV_RUNNING))
+			notify_ops->new_device(dev);
+}
+
+/*
+ * when virtio is stopped, qemu will send us the GET_VRING_BASE message.
+ */
+int
+user_get_vring_base(struct vhost_device_ctx ctx,
+	struct vhost_vring_state *state)
+{
+	struct virtio_net *dev = get_device(ctx);
+
+	/* We have to stop the queue (virtio) if it is running. */
+	if (dev->flags & VIRTIO_DEV_RUNNING)
+		notify_ops->destroy_device(dev);
+
+	/* Here we are safe to get the last used index */
+	ops->get_vring_base(ctx, state->index, state);
+
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"vring base idx:%d file:%d\n", state->index, state->num);
+	/*
+	 * Based on current qemu vhost-user implementation, this message is
+	 * sent and only sent in vhost_vring_stop.
+	 * TODO: cleanup the vring, it isn't usable since here.
+	 */
+	if (((int)dev->virtqueue[VIRTIO_RXQ]->callfd) >= 0) {
+		close(dev->virtqueue[VIRTIO_RXQ]->callfd);
+		dev->virtqueue[VIRTIO_RXQ]->callfd = (eventfd_t)-1;
+	}
+	if (((int)dev->virtqueue[VIRTIO_TXQ]->callfd) >= 0) {
+		close(dev->virtqueue[VIRTIO_TXQ]->callfd);
+		dev->virtqueue[VIRTIO_TXQ]->callfd = (eventfd_t)-1;
+	}
+
+	return 0;
+}
+
+void
+user_destroy_device(struct vhost_device_ctx ctx)
+{
+	struct virtio_net *dev = get_device(ctx);
+
+	if (dev && (dev->flags & VIRTIO_DEV_RUNNING))
+		notify_ops->destroy_device(dev);
+
+	if (dev && dev->mem) {
+		free_mem_region(dev);
+		free(dev->mem);
+		dev->mem = NULL;
+	}
+}
diff --git a/lib/librte_vhost/vhost_user/virtio-net-user.h b/lib/librte_vhost/vhost_user/virtio-net-user.h
new file mode 100644
index 0000000..df24860
--- /dev/null
+++ b/lib/librte_vhost/vhost_user/virtio-net-user.h
@@ -0,0 +1,49 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * 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.
+ *     * Neither the name of Intel Corporation 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 THE COPYRIGHT
+ *   OWNER 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.
+ */
+
+#ifndef _VIRTIO_NET_USER_H
+#define _VIRTIO_NET_USER_H
+
+#include "vhost-net.h"
+#include "vhost-net-user.h"
+
+int user_set_mem_table(struct vhost_device_ctx, struct VhostUserMsg *);
+
+void user_set_vring_call(struct vhost_device_ctx, struct VhostUserMsg *);
+
+void user_set_vring_kick(struct vhost_device_ctx, struct VhostUserMsg *);
+
+int user_get_vring_base(struct vhost_device_ctx, struct vhost_vring_state *);
+
+void user_destroy_device(struct vhost_device_ctx);
+#endif
diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c
index 3e73a35..9dea69c 100644
--- a/lib/librte_vhost/virtio-net.c
+++ b/lib/librte_vhost/virtio-net.c
@@ -92,8 +92,9 @@ qva_to_vva(struct virtio_net *dev, uint64_t qemu_va)
 		if ((qemu_va >= region->userspace_address) &&
 			(qemu_va <= region->userspace_address +
 			region->memory_size)) {
-			vhost_va = dev->mem->mapped_address + qemu_va -
-					dev->mem->base_address;
+			vhost_va = qemu_va + region->guest_phys_address +
+				region->address_offset -
+				region->userspace_address;
 			break;
 		}
 	}
@@ -260,6 +261,11 @@ init_device(struct virtio_net *dev)
 	memset(dev->virtqueue[VIRTIO_RXQ], 0, sizeof(struct vhost_virtqueue));
 	memset(dev->virtqueue[VIRTIO_TXQ], 0, sizeof(struct vhost_virtqueue));
 
+	dev->virtqueue[VIRTIO_RXQ]->kickfd = (eventfd_t)-1;
+	dev->virtqueue[VIRTIO_RXQ]->callfd = (eventfd_t)-1;
+	dev->virtqueue[VIRTIO_TXQ]->kickfd = (eventfd_t)-1;
+	dev->virtqueue[VIRTIO_TXQ]->callfd = (eventfd_t)-1;
+
 	/* Backends are set to -1 indicating an inactive device. */
 	dev->virtqueue[VIRTIO_RXQ]->backend = VIRTIO_DEV_STOPPED;
 	dev->virtqueue[VIRTIO_TXQ]->backend = VIRTIO_DEV_STOPPED;
@@ -576,7 +582,7 @@ set_vring_call(struct vhost_device_ctx ctx, struct vhost_vring_file *file)
 	/* file->index refers to the queue index. The txq is 1, rxq is 0. */
 	vq = dev->virtqueue[file->index];
 
-	if (vq->kickfd)
+	if ((int)vq->kickfd >= 0)
 		close((int)vq->kickfd);
 
 	vq->kickfd = file->fd;
@@ -602,8 +608,9 @@ set_vring_kick(struct vhost_device_ctx ctx, struct vhost_vring_file *file)
 	/* file->index refers to the queue index. The txq is 1, rxq is 0. */
 	vq = dev->virtqueue[file->index];
 
-	if (vq->callfd)
+	if ((int)vq->callfd >= 0)
 		close((int)vq->callfd);
+
 	vq->callfd = file->fd;
 
 	return 0;
-- 
1.9.3