diff mbox series

[23/28] net/vhost: add virtio-vhost-user support

Message ID	1560957293-17294-24-git-send-email-ndragazis@arrikto.com (mailing list archive)
State	RFC, archived
Delegated to:	Maxime Coquelin
Headers	From: Nikos Dragazis <ndragazis@arrikto.com> To: dev@dpdk.org Cc: Maxime Coquelin <maxime.coquelin@redhat.com>, Tiwei Bie <tiwei.bie@intel.com>, Zhihong Wang <zhihong.wang@intel.com>, Stefan Hajnoczi <stefanha@redhat.com>, Wei Wang <wei.w.wang@intel.com>, Stojaczyk Dariusz <dariusz.stojaczyk@intel.com>, Vangelis Koukis <vkoukis@arrikto.com> Date: Wed, 19 Jun 2019 18:14:48 +0300 Message-Id: <1560957293-17294-24-git-send-email-ndragazis@arrikto.com> In-Reply-To: <1560957293-17294-1-git-send-email-ndragazis@arrikto.com> References: <1560957293-17294-1-git-send-email-ndragazis@arrikto.com> Subject: [dpdk-dev] [PATCH 23/28] net/vhost: add virtio-vhost-user support Precedence: list Errors-To: dev-bounces@dpdk.org Sender: "dev" <dev-bounces@dpdk.org>
Series	vhost: add virtio-vhost-user transport \| [00/28] vhost: add virtio-vhost-user transport [01/28] vhost: introduce vhost transport operations structure [02/28] vhost: move socket management code [03/28] vhost: allocate per-socket transport state [04/28] vhost: move socket fd and un sockaddr [05/28] vhost: move start server/client calls [06/28] vhost: move vhost-user connection [07/28] vhost: move vhost-user reconnection [08/28] vhost: move vhost-user fdset [09/28] vhost: propagate vhost transport operations [10/28] vhost: use a single structure for the device state [11/28] vhost: extract socket I/O into transport [12/28] vhost: move slave request fd and lock [13/28] vhost: move mmap/munmap [14/28] vhost: move setup of the log memory region [15/28] vhost: remove main fd parameter from msg handlers [16/28] vhost: move postcopy live migration code [17/28] vhost: support registering additional vhost-user transports [18/28] drivers/virtio_vhost_user: add virtio PCI framework [19/28] vhost: add index field in vhost virtqueues [20/28] drivers: add virtio-vhost-user transport [21/28] drivers/virtio_vhost_user: use additional device resources [22/28] vhost: add flag for choosing vhost-user transport [23/28] net/vhost: add virtio-vhost-user support [24/28] examples/vhost_scsi: add --socket-file argument [25/28] examples/vhost_scsi: add virtio-vhost-user support [26/28] mk: link apps with virtio-vhost-user driver [27/28] config: add option for the virtio-vhost-user transport [28/28] usertools: add virtio-vhost-user devices to dpdk-devbind.py

Checks

Context	Check	Description
ci/checkpatch	success	coding style OK
ci/Intel-compilation	fail	Compilation issues

Commit Message

Nikos Dragazis June 19, 2019, 3:14 p.m. UTC

  The new virtio-transport=0|1 argument enables virtio-vhost-user support:

  testpmd ... --pci-whitelist 0000:00:04.0 \
              --vdev vhost,iface=0000:00:04.0,virtio-transport=1

Signed-off-by: Nikos Dragazis <ndragazis@arrikto.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 drivers/net/vhost/rte_eth_vhost.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff mbox series

Patch

diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c
index 0b61e37..c0d087f 100644
--- a/drivers/net/vhost/rte_eth_vhost.c
+++ b/drivers/net/vhost/rte_eth_vhost.c
@@ -31,6 +31,7 @@  enum {VIRTIO_RXQ, VIRTIO_TXQ, VIRTIO_QNUM};
 #define ETH_VHOST_DEQUEUE_ZERO_COPY	"dequeue-zero-copy"
 #define ETH_VHOST_IOMMU_SUPPORT		"iommu-support"
 #define ETH_VHOST_POSTCOPY_SUPPORT	"postcopy-support"
+#define ETH_VHOST_VIRTIO_TRANSPORT	"virtio-transport"
 #define VHOST_MAX_PKT_BURST 32
 
 static const char *valid_arguments[] = {
@@ -40,6 +41,7 @@  static const char *valid_arguments[] = {
 	ETH_VHOST_DEQUEUE_ZERO_COPY,
 	ETH_VHOST_IOMMU_SUPPORT,
 	ETH_VHOST_POSTCOPY_SUPPORT,
+	ETH_VHOST_VIRTIO_TRANSPORT,
 	NULL
 };
 
@@ -1341,6 +1343,7 @@  rte_pmd_vhost_probe(struct rte_vdev_device *dev)
 	int dequeue_zero_copy = 0;
 	int iommu_support = 0;
 	int postcopy_support = 0;
+	uint16_t virtio_transport = 0;
 	struct rte_eth_dev *eth_dev;
 	const char *name = rte_vdev_device_name(dev);
 
@@ -1422,6 +1425,16 @@  rte_pmd_vhost_probe(struct rte_vdev_device *dev)
 			flags |= RTE_VHOST_USER_POSTCOPY_SUPPORT;
 	}
 
+	if (rte_kvargs_count(kvlist, ETH_VHOST_VIRTIO_TRANSPORT) == 1) {
+		ret = rte_kvargs_process(kvlist, ETH_VHOST_VIRTIO_TRANSPORT,
+					 &open_int, &virtio_transport);
+		if (ret < 0)
+			goto out_free;
+
+		if (virtio_transport)
+			flags |= RTE_VHOST_USER_VIRTIO_TRANSPORT;
+	}
+
 	if (dev->device.numa_node == SOCKET_ID_ANY)
 		dev->device.numa_node = rte_socket_id();