vdpa: move file descriptor to vhost_vdpa_shared

Next patches will register the vhost_vdpa memory listener while the VM
is migrating at the destination, so we can map the memory to the device
before stopping the VM at the source.  The main goal is to reduce the
downtime.

However, the destination QEMU is unaware of which vhost_vdpa device will
register its memory_listener.  If the source guest has CVQ enabled, it
will be the CVQ device.  Otherwise, it  will be the first one.

Move the file descriptor to VhostVDPAShared so all vhost_vdpa can use
it, rather than always in the first / last vhost_vdpa.

Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20231221174322.3130442-7-eperezma@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

diff --git a/hw/virtio/vdpa-dev.c b/hw/virtio/vdpa-dev.c
index 457960d28aeeff4750307409fb1c3be36543b089..8774986571f4f7c47082987e10e374c50301ef27 100644 (file)
--- a/hw/virtio/vdpa-dev.c
+++ b/hw/virtio/vdpa-dev.c
@@ -66,7 +66,6 @@ static void vhost_vdpa_device_realize(DeviceState *dev, Error **errp)
     if (*errp) {
         return;
     }
-    v->vdpa.device_fd = v->vhostfd;
 
     v->vdev_id = vhost_vdpa_device_get_u32(v->vhostfd,
                                            VHOST_VDPA_GET_DEVICE_ID, errp);
@@ -115,6 +114,7 @@ static void vhost_vdpa_device_realize(DeviceState *dev, Error **errp)
         goto free_vqs;
     }
     v->vdpa.shared = g_new0(VhostVDPAShared, 1);
+    v->vdpa.shared->device_fd = v->vhostfd;
     v->vdpa.shared->iova_range = iova_range;
 
     ret = vhost_dev_init(&v->dev, &v->vdpa, VHOST_BACKEND_TYPE_VDPA, 0, NULL);

diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index 720cffbc089dbf4a9e9b0e5ab7d91f569cebf6d4..09df150ef2e83968805b96000661711ef3b04c57 100644 (file)
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -90,7 +90,7 @@ int vhost_vdpa_dma_map(struct vhost_vdpa *v, uint32_t asid, hwaddr iova,
                        hwaddr size, void *vaddr, bool readonly)
 {
     struct vhost_msg_v2 msg = {};
-    int fd = v->device_fd;
+    int fd = v->shared->device_fd;
     int ret = 0;
 
     msg.type = v->msg_type;
@@ -122,7 +122,7 @@ int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, uint32_t asid, hwaddr iova,
                          hwaddr size)
 {
     struct vhost_msg_v2 msg = {};
-    int fd = v->device_fd;
+    int fd = v->shared->device_fd;
     int ret = 0;
 
     msg.type = v->msg_type;
@@ -145,7 +145,7 @@ int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, uint32_t asid, hwaddr iova,
 
 static void vhost_vdpa_listener_begin_batch(struct vhost_vdpa *v)
 {
-    int fd = v->device_fd;
+    int fd = v->shared->device_fd;
     struct vhost_msg_v2 msg = {
         .type = v->msg_type,
         .iotlb.type = VHOST_IOTLB_BATCH_BEGIN,
@@ -174,7 +174,7 @@ static void vhost_vdpa_listener_commit(MemoryListener *listener)
     struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener);
     struct vhost_dev *dev = v->dev;
     struct vhost_msg_v2 msg = {};
-    int fd = v->device_fd;
+    int fd = v->shared->device_fd;
 
     if (!(dev->backend_cap & (0x1ULL << VHOST_BACKEND_F_IOTLB_BATCH))) {
         return;
@@ -499,7 +499,7 @@ static int vhost_vdpa_call(struct vhost_dev *dev, unsigned long int request,
                              void *arg)
 {
     struct vhost_vdpa *v = dev->opaque;
-    int fd = v->device_fd;
+    int fd = v->shared->device_fd;
     int ret;
 
     assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA);
@@ -661,7 +661,7 @@ static int vhost_vdpa_host_notifier_init(struct vhost_dev *dev, int queue_index)
     struct vhost_vdpa *v = dev->opaque;
     VirtIODevice *vdev = dev->vdev;
     VhostVDPAHostNotifier *n;
-    int fd = v->device_fd;
+    int fd = v->shared->device_fd;
     void *addr;
     char *name;
 
@@ -1290,7 +1290,7 @@ static void vhost_vdpa_suspend(struct vhost_dev *dev)
 
     if (dev->backend_cap & BIT_ULL(VHOST_BACKEND_F_SUSPEND)) {
         trace_vhost_vdpa_suspend(dev);
-        r = ioctl(v->device_fd, VHOST_VDPA_SUSPEND);
+        r = ioctl(v->shared->device_fd, VHOST_VDPA_SUSPEND);
         if (unlikely(r)) {
             error_report("Cannot suspend: %s(%d)", g_strerror(errno), errno);
         } else {

diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h
index 01e0f25e27abad7f3c90bc353b2de341a8b159f9..796a180afa9970af1cd6d50b2eaa5ca72426acdd 100644 (file)
--- a/include/hw/virtio/vhost-vdpa.h
+++ b/include/hw/virtio/vhost-vdpa.h
@@ -32,6 +32,7 @@ typedef struct VhostVDPAHostNotifier {
 
 /* Info shared by all vhost_vdpa device models */
 typedef struct vhost_vdpa_shared {
+    int device_fd;
     struct vhost_vdpa_iova_range iova_range;
 
     /* IOVA mapping used by the Shadow Virtqueue */
@@ -42,7 +43,6 @@ typedef struct vhost_vdpa_shared {
 } VhostVDPAShared;
 
 typedef struct vhost_vdpa {
-    int device_fd;
     int index;
     uint32_t msg_type;
     bool iotlb_batch_begin_sent;

diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index bf8e8327da49982ca2fb0508231707967ce45893..10cf0027de25799c3ee4763413607e3487424899 100644 (file)
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -235,14 +235,11 @@ static void vhost_vdpa_cleanup(NetClientState *nc)
         vhost_net_cleanup(s->vhost_net);
         g_free(s->vhost_net);
         s->vhost_net = NULL;
-    }
-     if (s->vhost_vdpa.device_fd >= 0) {
-        qemu_close(s->vhost_vdpa.device_fd);
-        s->vhost_vdpa.device_fd = -1;
     }
     if (s->vhost_vdpa.index != 0) {
         return;
     }
+    qemu_close(s->vhost_vdpa.shared->device_fd);
     g_free(s->vhost_vdpa.shared);
 }
 
@@ -448,7 +445,7 @@ static int vhost_vdpa_set_address_space_id(struct vhost_vdpa *v,
     };
     int r;
 
-    r = ioctl(v->device_fd, VHOST_VDPA_SET_GROUP_ASID, &asid);
+    r = ioctl(v->shared->device_fd, VHOST_VDPA_SET_GROUP_ASID, &asid);
     if (unlikely(r < 0)) {
         error_report("Can't set vq group %u asid %u, errno=%d (%s)",
                      asid.index, asid.num, errno, g_strerror(errno));
@@ -544,7 +541,7 @@ static int vhost_vdpa_net_cvq_start(NetClientState *nc)
         return 0;
     }
 
-    cvq_group = vhost_vdpa_get_vring_group(v->device_fd,
+    cvq_group = vhost_vdpa_get_vring_group(v->shared->device_fd,
                                            v->dev->vq_index_end - 1,
                                            &err);
     if (unlikely(cvq_group < 0)) {
@@ -1671,7 +1668,6 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
     qemu_set_info_str(nc, TYPE_VHOST_VDPA);
     s = DO_UPCAST(VhostVDPAState, nc, nc);
 
-    s->vhost_vdpa.device_fd = vdpa_device_fd;
     s->vhost_vdpa.index = queue_pair_index;
     s->always_svq = svq;
     s->migration_state.notify = NULL;
@@ -1680,6 +1676,7 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
         vhost_vdpa_net_valid_svq_features(features,
                                           &s->vhost_vdpa.migration_blocker);
         s->vhost_vdpa.shared = g_new0(VhostVDPAShared, 1);
+        s->vhost_vdpa.shared->device_fd = vdpa_device_fd;
         s->vhost_vdpa.shared->iova_range = iova_range;
         s->vhost_vdpa.shared->shadow_data = svq;
     } else if (!is_datapath) {