vhost-vdpa: introduce vhost-vdpa backend

Currently we have 2 types of vhost backends in QEMU: vhost kernel and
vhost-user. The above patch provides a generic device for vDPA purpose,
this vDPA device exposes to user space a non-vendor-specific configuration
interface for setting up a vhost HW accelerator, this patch set introduces
a third vhost backend called vhost-vdpa based on the vDPA interface.

Vhost-vdpa usage:

qemu-system-x86_64 -cpu host -enable-kvm \
    ......
    -netdev type=vhost-vdpa,vhostdev=/dev/vhost-vdpa-id,id=vhost-vdpa0 \
    -device virtio-net-pci,netdev=vhost-vdpa0,page-per-vq=on \

Signed-off-by: Lingshan zhu <[email protected]>
Signed-off-by: Tiwei Bie <[email protected]>
Signed-off-by: Cindy Lu <[email protected]>
Signed-off-by: Jason Wang <[email protected]>
Message-Id: <[email protected]>
Reviewed-by: Michael S. Tsirkin <[email protected]>
Signed-off-by: Michael S. Tsirkin <[email protected]>
Acked-by: Jason Wang <[email protected]>

Author: lulu-github-name

configure

@@ -1575,6 +1575,10 @@ for opt do
   ;;
   --enable-vhost-user) vhost_user="yes"
   ;;
+  --disable-vhost-vdpa) vhost_vdpa="no"
+  ;;
+  --enable-vhost-vdpa) vhost_vdpa="yes"
+  ;;
   --disable-vhost-kernel) vhost_kernel="no"
   ;;
   --enable-vhost-kernel) vhost_kernel="yes"
@@ -1883,6 +1887,7 @@ disabled with --disable-FEATURE, default is enabled if available:
   vhost-crypto    vhost-user-crypto backend support
   vhost-kernel    vhost kernel backend support
   vhost-user      vhost-user backend support
+  vhost-vdpa      vhost-vdpa kernel backend support
   spice           spice
   rbd             rados block device (rbd)
   libiscsi        iscsi support
@@ -2394,6 +2399,10 @@ test "$vhost_user" = "" && vhost_user=yes
 if test "$vhost_user" = "yes" && test "$mingw32" = "yes"; then
   error_exit "vhost-user isn't available on win32"
 fi
+test "$vhost_vdpa" = "" && vhost_vdpa=$linux
+if test "$vhost_vdpa" = "yes" && test "$linux" != "yes"; then
+  error_exit "vhost-vdpa is only available on Linux"
+fi
 test "$vhost_kernel" = "" && vhost_kernel=$linux
 if test "$vhost_kernel" = "yes" && test "$linux" != "yes"; then
   error_exit "vhost-kernel is only available on Linux"
@@ -2422,6 +2431,11 @@ test "$vhost_user_fs" = "" && vhost_user_fs=$vhost_user
 if test "$vhost_user_fs" = "yes" && test "$vhost_user" = "no"; then
   error_exit "--enable-vhost-user-fs requires --enable-vhost-user"
 fi
+#vhost-vdpa backends
+test "$vhost_net_vdpa" = "" && vhost_net_vdpa=$vhost_vdpa
+if test "$vhost_net_vdpa" = "yes" && test "$vhost_vdpa" = "no"; then
+  error_exit "--enable-vhost-net-vdpa requires --enable-vhost-vdpa"
+fi
 
 # OR the vhost-kernel and vhost-user values for simplicity
 if test "$vhost_net" = ""; then
@@ -6936,6 +6950,7 @@ echo "vhost-scsi support $vhost_scsi"
 echo "vhost-vsock support $vhost_vsock"
 echo "vhost-user support $vhost_user"
 echo "vhost-user-fs support $vhost_user_fs"
+echo "vhost-vdpa support $vhost_vdpa"
 echo "Trace backends    $trace_backends"
 if have_backend "simple"; then
 echo "Trace output file $trace_file-<pid>"
@@ -7437,6 +7452,9 @@ fi
 if test "$vhost_net_user" = "yes" ; then
   echo "CONFIG_VHOST_NET_USER=y" >> $config_host_mak
 fi
+if test "$vhost_net_vdpa" = "yes" ; then
+  echo "CONFIG_VHOST_NET_VDPA=y" >> $config_host_mak
+fi
 if test "$vhost_crypto" = "yes" ; then
   echo "CONFIG_VHOST_CRYPTO=y" >> $config_host_mak
 fi
@@ -7452,6 +7470,9 @@ fi
 if test "$vhost_user" = "yes" ; then
   echo "CONFIG_VHOST_USER=y" >> $config_host_mak
 fi
+if test "$vhost_vdpa" = "yes" ; then
+  echo "CONFIG_VHOST_VDPA=y" >> $config_host_mak
+fi
 if test "$vhost_user_fs" = "yes" ; then
   echo "CONFIG_VHOST_USER_FS=y" >> $config_host_mak
 fi

docs/interop/index.rst

@@ -20,3 +20,4 @@ Contents:
    qemu-ga
    vhost-user
    vhost-user-gpu
+   vhost-vdpa

docs/interop/vhost-vdpa.rst

@@ -0,0 +1,17 @@
+=====================
+Vhost-vdpa Protocol
+=====================
+
+Introduction
+=============
+vDPA(Virtual data path acceleration) device is a device that uses
+a datapath which complies with the virtio specifications with vendor
+specific control path. vDPA devices can be both physically located on
+the hardware or emulated by software.
+
+This document describes the vDPA support in qemu
+
+Here is the kernel commit here
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=4c8cf31885f69e86be0b5b9e6677a26797365e1d
+
+TODO : More information will add later

hw/net/vhost_net.c

@@ -17,6 +17,7 @@
 #include "net/net.h"
 #include "net/tap.h"
 #include "net/vhost-user.h"
+#include "net/vhost-vdpa.h"
 
 #include "standard-headers/linux/vhost_types.h"
 #include "hw/virtio/virtio-net.h"
@@ -33,12 +34,6 @@
 #include "hw/virtio/vhost.h"
 #include "hw/virtio/virtio-bus.h"
 
-struct vhost_net {
-    struct vhost_dev dev;
-    struct vhost_virtqueue vqs[2];
-    int backend;
-    NetClientState *nc;
-};
 
 /* Features supported by host kernel. */
 static const int kernel_feature_bits[] = {
@@ -96,6 +91,11 @@ static const int *vhost_net_get_feature_bits(struct vhost_net *net)
     case NET_CLIENT_DRIVER_VHOST_USER:
         feature_bits = user_feature_bits;
         break;
+#ifdef CONFIG_VHOST_NET_VDPA
+    case NET_CLIENT_DRIVER_VHOST_VDPA:
+        feature_bits = vdpa_feature_bits;
+        break;
+#endif
     default:
         error_report("Feature bits not defined for this type: %d",
                 net->nc->info->type);
@@ -443,6 +443,12 @@ VHostNetState *get_vhost_net(NetClientState *nc)
         vhost_net = vhost_user_get_vhost_net(nc);
         assert(vhost_net);
         break;
+#endif
+#ifdef CONFIG_VHOST_NET_VDPA
+    case NET_CLIENT_DRIVER_VHOST_VDPA:
+        vhost_net = vhost_vdpa_get_vhost_net(nc);
+        assert(vhost_net);
+        break;
 #endif
     default:
         break;

hw/net/virtio-net.c

@@ -43,6 +43,7 @@
 #include "monitor/qdev.h"
 #include "hw/pci/pci.h"
 #include "net_rx_pkt.h"
+#include "hw/virtio/vhost.h"
 
 #define VIRTIO_NET_VM_VERSION    11
 
@@ -125,6 +126,8 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config)
     VirtIONet *n = VIRTIO_NET(vdev);
     struct virtio_net_config netcfg;
 
+    int ret = 0;
+    memset(&netcfg, 0 , sizeof(struct virtio_net_config));
     virtio_stw_p(vdev, &netcfg.status, n->status);
     virtio_stw_p(vdev, &netcfg.max_virtqueue_pairs, n->max_queues);
     virtio_stw_p(vdev, &netcfg.mtu, n->net_conf.mtu);
@@ -138,6 +141,15 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config)
     virtio_stl_p(vdev, &netcfg.supported_hash_types,
                  VIRTIO_NET_RSS_SUPPORTED_HASHES);
     memcpy(config, &netcfg, n->config_size);
+
+    NetClientState *nc = qemu_get_queue(n->nic);
+    if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) {
+        ret = vhost_net_get_config(get_vhost_net(nc->peer), (uint8_t *)&netcfg,
+                             n->config_size);
+    if (ret != -1) {
+        memcpy(config, &netcfg, n->config_size);
+    }
+    }
 }
 
 static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config)
@@ -153,6 +165,13 @@ static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config)
         memcpy(n->mac, netcfg.mac, ETH_ALEN);
         qemu_format_nic_info_str(qemu_get_queue(n->nic), n->mac);
     }
+
+    NetClientState *nc = qemu_get_queue(n->nic);
+    if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) {
+        vhost_net_set_config(get_vhost_net(nc->peer), (uint8_t *)&netcfg,
+                               0, n->config_size,
+                        VHOST_SET_CONFIG_TYPE_MASTER);
+      }
 }
 
 static bool virtio_net_started(VirtIONet *n, uint8_t status)

hw/virtio/Makefile.objs

@@ -5,6 +5,7 @@ obj-y += virtio.o
 obj-$(CONFIG_VHOST) += vhost.o vhost-backend.o
 common-obj-$(call lnot,$(CONFIG_VHOST)) += vhost-stub.o
 obj-$(CONFIG_VHOST_USER) += vhost-user.o
+obj-$(CONFIG_VHOST_VDPA) += vhost-vdpa.o
 
 common-obj-$(CONFIG_VIRTIO_RNG) += virtio-rng.o
 common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o

hw/virtio/vhost-backend.c

@@ -15,6 +15,7 @@
 #include "qemu/main-loop.h"
 #include "standard-headers/linux/vhost_types.h"
 
+#include "hw/virtio/vhost-vdpa.h"
 #ifdef CONFIG_VHOST_KERNEL
 #include <linux/vhost.h>
 #include <sys/ioctl.h>
@@ -285,6 +286,11 @@ int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)
     case VHOST_BACKEND_TYPE_USER:
         dev->vhost_ops = &user_ops;
         break;
+#endif
+#ifdef CONFIG_VHOST_VDPA
+    case VHOST_BACKEND_TYPE_VDPA:
+        dev->vhost_ops = &vdpa_ops;
+        break;
 #endif
     default:
         error_report("Unknown vhost backend type");