[RFC PATCH] Allow VIRTIO_F_IN_ORDER to be negotiated for vdpa devices

[gautam.dawar]

From: Gautam Dawar <gdawar@xilinx.com>

Hi All,

The VIRTIO_F_IN_ORDER feature is implemented by DPDK's virtio_net
driver but not by the Linux kernel's virtio_net driver.
However, this feature still can't be tested using vhost-vdpa with
hardware devices that implement it as VIRTIO_F_IN_ORDER isn't defined
in kernel's virtio_config.h header file.
This patch adds the ability to negotiate VIRTIO_F_IN_ORDER bit for
vhost-vdpa backend when the underlying device supports this feature.
This would be useful for benchmarking the performance improvements
for HW devices that implement this feature. At the same time, it
shouldn't have any negative impact as vhost-vdpa backend doesn't
involve any userspace virtqueue operations.
In the final patch, instead of making a direct change in
virtio_config.h, it will be pushed in the kernel and then QEMU's
file will be synced with it, as usual.

Signed-off-by: Gautam Dawar <gdawar@xilinx.com>
---
 hw/net/virtio-net.c                            | 10 ++++++++++
 include/standard-headers/linux/virtio_config.h |  6 ++++++
 net/vhost-vdpa.c                               |  1 +
 3 files changed, 17 insertions(+)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index cf8ab0f8af..a1089d06f6 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -3507,11 +3507,21 @@ static void virtio_net_device_realize(DeviceState *dev, 
Error **errp)
     nc->rxfilter_notify_enabled = 1;
 
    if (nc->peer && nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) {
+        uint64_t features = BIT_ULL(VIRTIO_F_IN_ORDER);
         struct virtio_net_config netcfg = {};
+
         memcpy(&netcfg.mac, &n->nic_conf.macaddr, ETH_ALEN);
         vhost_net_set_config(get_vhost_net(nc->peer),
             (uint8_t *)&netcfg, 0, ETH_ALEN, VHOST_SET_CONFIG_TYPE_MASTER);
+
+       /*
+         * For vhost-vdpa, if underlying device supports IN_ORDER feature,
+         * make it available for negotiation.
+         */
+       features = vhost_net_get_features(get_vhost_net(nc->peer), features);
+       n->host_features |= features;
     }
+
     QTAILQ_INIT(&n->rsc_chains);
     n->qdev = dev;
 
diff --git a/include/standard-headers/linux/virtio_config.h 
b/include/standard-headers/linux/virtio_config.h
index 22e3a85f67..9ec3a8b54b 100644
--- a/include/standard-headers/linux/virtio_config.h
+++ b/include/standard-headers/linux/virtio_config.h
@@ -80,6 +80,12 @@
 /* This feature indicates support for the packed virtqueue layout. */
 #define VIRTIO_F_RING_PACKED           34
 
+/*
+ * Inorder feature indicates that all buffers are used by the device
+ * in the same order in which they have been made available.
+ */
+#define VIRTIO_F_IN_ORDER 35
+
 /*
  * This feature indicates that memory accesses by the driver and the
  * device are ordered in a way described by the platform.
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index 25dd6dd975..2886cba5ec 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -62,6 +62,7 @@ const int vdpa_feature_bits[] = {
     VIRTIO_NET_F_CTRL_VQ,
     VIRTIO_F_IOMMU_PLATFORM,
     VIRTIO_F_RING_PACKED,
+    VIRTIO_F_IN_ORDER,
     VIRTIO_NET_F_RSS,
     VIRTIO_NET_F_HASH_REPORT,
     VIRTIO_NET_F_GUEST_ANNOUNCE,
-- 
2.30.1