[PATCH v7] net/virtio-user: add support for server mode

[zhiyong.yang@intel.com]

In a container environment if the vhost-user backend restarts, there's
no way for it to reconnect to virtio-user. To address this, support for
server mode is added. In this mode the socket file is created by virtio-
user, which the backend then connects to. This means that if the backend
restarts, it can reconnect to virtio-user and continue communications.

With current implementation, LSC is enabled at virtio-user side to
support to accept the coming connection.

Server mode virtio-user only supports to work with vhost-user.

Release note is updated in this patch.

Signed-off-by: Zhiyong Yang <zhiyong.yang@intel.com>
---

Cc: maxime.coquelin@redhat.com
Cc: jianfeng.tan@intel.com
Cc: tiwei.bie@intel.com
Cc: zhihong.wang@intel.com
Cc: dong1.wang@intel.com
Cc: thomas@monjalon.net

Changes in V7:
1. avoid misusing vhost-kernel in server mode virtio-user.
2. move the funciton definition is_vhost_user_by_type before 
virtio_user_start_device in order that it can be called.
3. add comments in the code to state feature negotiation limit.

Changes in V6:
1. fix report wrong link stauts in server mode.
2. fix some code style issues.

Changes in V5:
1. Support server mode virtio-user startup in non-blocking mode.
2. rebase on top of dpdk-next-virtio.

Changes in V4:
1. Don't create new pthread any more and use librte_eal interrupt thread
instead. 

Changes in V3:
1. use EAL epoll mechanism instead of vhost events. Cancel to export vhost
event APIs.
2. rebase the code on top of dpdk-next-virtio

Changes in V2:
1. split two patches 1/5 and 2/5 from v1 patchset to fix some existing issues
which is not strongly related to support for server mode
2. move fdset related functions to librte_eal from librte_vhost exposed as
new APIs.
3. release note is added in the patch 5/5.
4. squash data structure change patch into 4/5 according to Maxime's suggestion.

 doc/guides/rel_notes/release_18_05.rst           |   6 ++
 drivers/net/virtio/virtio_user/vhost_user.c      |  45 ++++++++--
 drivers/net/virtio/virtio_user/virtio_user_dev.c | 101 ++++++++++++++++-------
 drivers/net/virtio/virtio_user/virtio_user_dev.h |   3 +
 drivers/net/virtio/virtio_user_ethdev.c          | 101 ++++++++++++++++++++---
 5 files changed, 209 insertions(+), 47 deletions(-)

diff --git a/doc/guides/rel_notes/release_18_05.rst b/doc/guides/rel_notes/release_18_05.rst
index 9cc77f893..f8897b2e9 100644
--- a/doc/guides/rel_notes/release_18_05.rst
+++ b/doc/guides/rel_notes/release_18_05.rst
@@ -58,6 +58,12 @@ New Features
   * Added support for NVGRE, VXLAN and GENEVE filters in flow API.
   * Added support for DROP action in flow API.
 
+* **Added support for virtio-user server mode.**
+  In a container environment if the vhost-user backend restarts, there's no way
+  for it to reconnect to virtio-user. To address this, support for server mode
+  is added. In this mode the socket file is created by virtio-user, which the
+  backend connects to. This means that if the backend restarts, it can reconnect
+  to virtio-user and continue communications.
 
 API Changes
 -----------
diff --git a/drivers/net/virtio/virtio_user/vhost_user.c b/drivers/net/virtio/virtio_user/vhost_user.c
index 91c6449bb..a6df97a00 100644
--- a/drivers/net/virtio/virtio_user/vhost_user.c
+++ b/drivers/net/virtio/virtio_user/vhost_user.c
@@ -378,6 +378,30 @@ vhost_user_sock(struct virtio_user_dev *dev,
 	return 0;
 }
 
+#define MAX_VIRTIO_USER_BACKLOG 1
+static int
+virtio_user_start_server(struct virtio_user_dev *dev, struct sockaddr_un *un)
+{
+	int ret;
+	int flag;
+	int fd = dev->listenfd;
+
+	ret = bind(fd, (struct sockaddr *)un, sizeof(*un));
+	if (ret < 0) {
+		PMD_DRV_LOG(ERR, "failed to bind to %s: %s; remove it and try again\n",
+			    dev->path, strerror(errno));
+		return -1;
+	}
+	ret = listen(fd, MAX_VIRTIO_USER_BACKLOG);
+	if (ret < 0)
+		return -1;
+
+	flag = fcntl(fd, F_GETFL);
+	fcntl(fd, F_SETFL, flag | O_NONBLOCK);
+
+	return 0;
+}
+
 /**
  * Set up environment to talk with a vhost user backend.
  *
@@ -405,13 +429,24 @@ vhost_user_setup(struct virtio_user_dev *dev)
 	memset(&un, 0, sizeof(un));
 	un.sun_family = AF_UNIX;
 	snprintf(un.sun_path, sizeof(un.sun_path), "%s", dev->path);
-	if (connect(fd, (struct sockaddr *)&un, sizeof(un)) < 0) {
-		PMD_DRV_LOG(ERR, "connect error, %s", strerror(errno));
-		close(fd);
-		return -1;
+
+	if (dev->is_server) {
+		dev->listenfd = fd;
+		if (virtio_user_start_server(dev, &un) < 0) {
+			PMD_DRV_LOG(ERR, "virtio-user startup fails in server mode");
+			close(fd);
+			return -1;
+		}
+		dev->vhostfd = -1;
+	} else {
+		if (connect(fd, (struct sockaddr *)&un, sizeof(un)) < 0) {
+			PMD_DRV_LOG(ERR, "connect error, %s", strerror(errno));
+			close(fd);
+			return -1;
+		}
+		dev->vhostfd = fd;
 	}
 
-	dev->vhostfd = fd;
 	return 0;
 }
 
diff --git a/drivers/net/virtio/virtio_user/virtio_user_dev.c b/drivers/net/virtio/virtio_user/virtio_user_dev.c
index f90fee9e5..38b8bc90d 100644
--- a/drivers/net/virtio/virtio_user/virtio_user_dev.c
+++ b/drivers/net/virtio/virtio_user/virtio_user_dev.c
@@ -93,12 +93,26 @@ virtio_user_queue_setup(struct virtio_user_dev *dev,
 	return 0;
 }
 
+int
+is_vhost_user_by_type(const char *path)
+{
+	struct stat sb;
+
+	if (stat(path, &sb) == -1)
+		return 0;
+
+	return S_ISSOCK(sb.st_mode);
+}
+
 int
 virtio_user_start_device(struct virtio_user_dev *dev)
 {
 	uint64_t features;
 	int ret;
 
+	if (is_vhost_user_by_type(dev->path) && dev->vhostfd < 0)
+		return -1;
+
 	/* Do not check return as already done in init, or reset in stop */
 	dev->ops->send_request(dev, VHOST_USER_SET_OWNER, NULL);
 
@@ -174,17 +188,6 @@ parse_mac(struct virtio_user_dev *dev, const char *mac)
 	}
 }
 
-int
-is_vhost_user_by_type(const char *path)
-{
-	struct stat sb;
-
-	if (stat(path, &sb) == -1)
-		return 0;
-
-	return S_ISSOCK(sb.st_mode);
-}
-
 static int
 virtio_user_dev_init_notify(struct virtio_user_dev *dev)
 {
@@ -254,6 +257,8 @@ virtio_user_fill_intr_handle(struct virtio_user_dev *dev)
 	eth_dev->intr_handle->fd = -1;
 	if (dev->vhostfd >= 0)
 		eth_dev->intr_handle->fd = dev->vhostfd;
+	else if (dev->is_server)
+		eth_dev->intr_handle->fd = dev->listenfd;
 
 	return 0;
 }
@@ -267,21 +272,32 @@ virtio_user_dev_setup(struct virtio_user_dev *dev)
 	dev->vhostfds = NULL;
 	dev->tapfds = NULL;
 
-	if (is_vhost_user_by_type(dev->path)) {
-		dev->ops = &ops_user;
-	} else {
-		dev->ops = &ops_kernel;
-
-		dev->vhostfds = malloc(dev->max_queue_pairs * sizeof(int));
-		dev->tapfds = malloc(dev->max_queue_pairs * sizeof(int));
-		if (!dev->vhostfds || !dev->tapfds) {
-			PMD_INIT_LOG(ERR, "Failed to malloc");
+	if (dev->is_server) {
+		if (access(dev->path, F_OK) == 0 &&
+		    !is_vhost_user_by_type(dev->path)) {
+			PMD_DRV_LOG(ERR, "Server mode doesn't support vhost-kernel!");
 			return -1;
 		}
-
-		for (q = 0; q < dev->max_queue_pairs; ++q) {
-			dev->vhostfds[q] = -1;
-			dev->tapfds[q] = -1;
+		dev->ops = &ops_user;
+	} else {
+		if (is_vhost_user_by_type(dev->path)) {
+			dev->ops = &ops_user;
+		} else {
+			dev->ops = &ops_kernel;
+
+			dev->vhostfds = malloc(dev->max_queue_pairs *
+					       sizeof(int));
+			dev->tapfds = malloc(dev->max_queue_pairs *
+					     sizeof(int));
+			if (!dev->vhostfds || !dev->tapfds) {
+				PMD_INIT_LOG(ERR, "Failed to malloc");
+				return -1;
+			}
+
+			for (q = 0; q < dev->max_queue_pairs; ++q) {
+				dev->vhostfds[q] = -1;
+				dev->tapfds[q] = -1;
+			}
 		}
 	}
 
@@ -337,16 +353,29 @@ virtio_user_dev_init(struct virtio_user_dev *dev, char *path, int queues,
 		return -1;
 	}
 
-	if (dev->ops->send_request(dev, VHOST_USER_SET_OWNER, NULL) < 0) {
-		PMD_INIT_LOG(ERR, "set_owner fails: %s", strerror(errno));
-		return -1;
-	}
+	if (dev->vhostfd >= 0) {
+		if (dev->ops->send_request(dev, VHOST_USER_SET_OWNER,
+					   NULL) < 0) {
+			PMD_INIT_LOG(ERR, "set_owner fails: %s",
+				     strerror(errno));
+			return -1;
+		}
 
-	if (dev->ops->send_request(dev, VHOST_USER_GET_FEATURES,
-			    &dev->device_features) < 0) {
-		PMD_INIT_LOG(ERR, "get_features failed: %s", strerror(errno));
-		return -1;
+		if (dev->ops->send_request(dev, VHOST_USER_GET_FEATURES,
+					   &dev->device_features) < 0) {
+			PMD_INIT_LOG(ERR, "get_features failed: %s",
+				     strerror(errno));
+			return -1;
+		}
+	} else {
+		/* We just pretend vhost-user can support all these features.
+		 * Note that this could be problematic that if some feature is
+		 * negotiated but not supported by the vhost-user which comes
+		 * later.
+		 */
+		dev->device_features = VIRTIO_USER_SUPPORTED_FEATURES;
 	}
+
 	if (dev->mac_specified)
 		dev->device_features |= (1ull << VIRTIO_NET_F_MAC);
 
@@ -388,6 +417,11 @@ virtio_user_dev_uninit(struct virtio_user_dev *dev)
 
 	close(dev->vhostfd);
 
+	if (dev->is_server && dev->listenfd >= 0) {
+		close(dev->listenfd);
+		dev->listenfd = -1;
+	}
+
 	if (dev->vhostfds) {
 		for (i = 0; i < dev->max_queue_pairs; ++i)
 			close(dev->vhostfds[i]);
@@ -396,6 +430,9 @@ virtio_user_dev_uninit(struct virtio_user_dev *dev)
 	}
 
 	free(dev->ifname);
+
+	if (dev->is_server)
+		unlink(dev->path);
 }
 
 static uint8_t
diff --git a/drivers/net/virtio/virtio_user/virtio_user_dev.h b/drivers/net/virtio/virtio_user/virtio_user_dev.h
index 5f8755771..ade727e46 100644
--- a/drivers/net/virtio/virtio_user/virtio_user_dev.h
+++ b/drivers/net/virtio/virtio_user/virtio_user_dev.h
@@ -6,6 +6,7 @@
 #define _VIRTIO_USER_DEV_H
 
 #include <limits.h>
+#include <stdbool.h>
 #include "../virtio_pci.h"
 #include "../virtio_ring.h"
 #include "vhost.h"
@@ -13,6 +14,8 @@
 struct virtio_user_dev {
 	/* for vhost_user backend */
 	int		vhostfd;
+	int		listenfd;   /* listening fd */
+	bool		is_server;  /* server or client mode */
 
 	/* for vhost_kernel backend */
 	char		*ifname;
diff --git a/drivers/net/virtio/virtio_user_ethdev.c b/drivers/net/virtio/virtio_user_ethdev.c
index 263649006..4e7b3c34f 100644
--- a/drivers/net/virtio/virtio_user_ethdev.c
+++ b/drivers/net/virtio/virtio_user_ethdev.c
@@ -24,15 +24,73 @@
 #define virtio_user_get_dev(hw) \
 	((struct virtio_user_dev *)(hw)->virtio_user_dev)
 
+static int
+virtio_user_server_reconnect(struct virtio_user_dev *dev)
+{
+	int ret;
+	int flag;
+	int connectfd;
+	struct rte_eth_dev *eth_dev = &rte_eth_devices[dev->port_id];
+
+	connectfd = accept(dev->listenfd, NULL, NULL);
+	if (connectfd < 0)
+		return -1;
+
+	dev->vhostfd = connectfd;
+	flag = fcntl(connectfd, F_GETFD);
+	fcntl(connectfd, F_SETFL, flag | O_NONBLOCK);
+
+	ret = virtio_user_start_device(dev);
+	if (ret < 0)
+		return -1;
+
+	if (eth_dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC) {
+		if (rte_intr_disable(eth_dev->intr_handle) < 0) {
+			PMD_DRV_LOG(ERR, "interrupt disable failed");
+			return -1;
+		}
+		rte_intr_callback_unregister(eth_dev->intr_handle,
+					     virtio_interrupt_handler,
+					     eth_dev);
+		eth_dev->intr_handle->fd = connectfd;
+		rte_intr_callback_register(eth_dev->intr_handle,
+					   virtio_interrupt_handler, eth_dev);
+
+		if (rte_intr_enable(eth_dev->intr_handle) < 0) {
+			PMD_DRV_LOG(ERR, "interrupt enable failed");
+			return -1;
+		}
+	}
+	PMD_INIT_LOG(NOTICE, "server mode virtio-user reconnection succeeds!");
+	return 0;
+}
+
 static void
 virtio_user_delayed_handler(void *param)
 {
 	struct virtio_hw *hw = (struct virtio_hw *)param;
-	struct rte_eth_dev *dev = &rte_eth_devices[hw->port_id];
+	struct rte_eth_dev *eth_dev = &rte_eth_devices[hw->port_id];
+	struct virtio_user_dev *dev = virtio_user_get_dev(hw);
 
-	rte_intr_callback_unregister(dev->intr_handle,
-				     virtio_interrupt_handler,
-				     dev);
+	if (rte_intr_disable(eth_dev->intr_handle) < 0) {
+		PMD_DRV_LOG(ERR, "interrupt disable failed");
+		return;
+	}
+	rte_intr_callback_unregister(eth_dev->intr_handle,
+				     virtio_interrupt_handler, eth_dev);
+	if (dev->is_server) {
+		if (dev->vhostfd >= 0) {
+			close(dev->vhostfd);
+			dev->vhostfd = -1;
+		}
+		eth_dev->intr_handle->fd = dev->listenfd;
+		rte_intr_callback_register(eth_dev->intr_handle,
+					   virtio_interrupt_handler, eth_dev);
+		if (rte_intr_enable(eth_dev->intr_handle) < 0) {
+			PMD_DRV_LOG(ERR, "interrupt enable failed");
+			return;
+		}
+	}
 }
 
 static void
@@ -67,12 +125,10 @@ virtio_user_read_dev_config(struct virtio_hw *hw, size_t offset,
 				dev->status &= (~VIRTIO_NET_S_LINK_UP);
 				PMD_DRV_LOG(ERR, "virtio-user port %u is down",
 					    hw->port_id);
-				/* Only client mode is available now. Once the
-				 * connection is broken, it can never be up
-				 * again. Besides, this function could be called
-				 * in the process of interrupt handling,
-				 * callback cannot be unregistered here, set an
-				 * alarm to do it.
+
+				/* This function could be called in the process
+				 * of interrupt handling, callback cannot be
+				 * unregistered here, set an alarm to do it.
 				 */
 				rte_eal_alarm_set(1,
 						  virtio_user_delayed_handler,
@@ -85,7 +141,12 @@ virtio_user_read_dev_config(struct virtio_hw *hw, size_t offset,
 				PMD_DRV_LOG(ERR, "error clearing O_NONBLOCK flag");
 				return;
 			}
+		} else if (dev->is_server) {
+			dev->status &= (~VIRTIO_NET_S_LINK_UP);
+			if (virtio_user_server_reconnect(dev) >= 0)
+				dev->status |= VIRTIO_NET_S_LINK_UP;
 		}
+
 		*(uint16_t *)dst = dev->status;
 	}
 
@@ -278,12 +339,15 @@ static const char *valid_args[] = {
 	VIRTIO_USER_ARG_QUEUE_SIZE,
 #define VIRTIO_USER_ARG_INTERFACE_NAME "iface"
 	VIRTIO_USER_ARG_INTERFACE_NAME,
+#define VIRTIO_USER_ARG_SERVER_MODE "server"
+	VIRTIO_USER_ARG_SERVER_MODE,
 	NULL
 };
 
 #define VIRTIO_USER_DEF_CQ_EN	0
 #define VIRTIO_USER_DEF_Q_NUM	1
 #define VIRTIO_USER_DEF_Q_SZ	256
+#define VIRTIO_USER_DEF_SERVER_MODE	0
 
 static int
 get_string_arg(const char *key __rte_unused,
@@ -378,6 +442,7 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
 	uint64_t queues = VIRTIO_USER_DEF_Q_NUM;
 	uint64_t cq = VIRTIO_USER_DEF_CQ_EN;
 	uint64_t queue_size = VIRTIO_USER_DEF_Q_SZ;
+	uint64_t server_mode = VIRTIO_USER_DEF_SERVER_MODE;
 	char *path = NULL;
 	char *ifname = NULL;
 	char *mac_addr = NULL;
@@ -445,6 +510,15 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
 		}
 	}
 
+	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_SERVER_MODE) == 1) {
+		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_SERVER_MODE,
+				       &get_integer_arg, &server_mode) < 0) {
+			PMD_INIT_LOG(ERR, "error to parse %s",
+				     VIRTIO_USER_ARG_SERVER_MODE);
+			goto end;
+		}
+	}
+
 	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_CQ_NUM) == 1) {
 		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_CQ_NUM,
 				       &get_integer_arg, &cq) < 0) {
@@ -469,6 +543,8 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
 	}
 
 	if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+		struct virtio_user_dev *vu_dev;
+
 		eth_dev = virtio_user_eth_dev_alloc(dev);
 		if (!eth_dev) {
 			PMD_INIT_LOG(ERR, "virtio_user fails to alloc device");
@@ -476,6 +552,11 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
 		}
 
 		hw = eth_dev->data->dev_private;
+		vu_dev = virtio_user_get_dev(hw);
+		if (server_mode == 1)
+			vu_dev->is_server = true;
+		else
+			vu_dev->is_server = false;
 		if (virtio_user_dev_init(hw->virtio_user_dev, path, queues, cq,
 				 queue_size, mac_addr, &ifname) < 0) {
 			PMD_INIT_LOG(ERR, "virtio_user_dev_init fails");
-- 
2.14.3