@@ -26,12 +26,15 @@
#include <err.h>
#include "standard-headers/linux/virtio_net.h"
#include "monitor/monitor.h"
+#include "migration/migration.h"
+#include "migration/misc.h"
#include "hw/virtio/vhost.h"
/* Todo:need to add the multiqueue support here */
typedef struct VhostVDPAState {
NetClientState nc;
struct vhost_vdpa vhost_vdpa;
+ Notifier migration_state;
VHostNetState *vhost_net;
/* Control commands shadow buffers */
@@ -241,10 +244,79 @@ static VhostVDPAState *vhost_vdpa_net_first_nc_vdpa(VhostVDPAState *s)
return DO_UPCAST(VhostVDPAState, nc, nc0);
}
+static void vhost_vdpa_net_log_global_enable(VhostVDPAState *s, bool enable)
+{
+ struct vhost_vdpa *v = &s->vhost_vdpa;
+ VirtIONet *n;
+ VirtIODevice *vdev;
+ int data_queue_pairs, cvq, r;
+ NetClientState *peer;
+
+ /* We are only called on the first data vqs and only if x-svq is not set */
+ if (s->vhost_vdpa.shadow_vqs_enabled == enable) {
+ return;
+ }
+
+ vdev = v->dev->vdev;
+ n = VIRTIO_NET(vdev);
+ if (!n->vhost_started) {
+ return;
+ }
+
+ data_queue_pairs = n->multiqueue ? n->max_queue_pairs : 1;
+ cvq = virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ) ?
+ n->max_ncs - n->max_queue_pairs : 0;
+ /*
+ * TODO: vhost_net_stop does suspend, get_base and reset. We can be smarter
+ * in the future and resume the device if read-only operations between
+ * suspend and reset goes wrong.
+ */
+ vhost_net_stop(vdev, n->nic->ncs, data_queue_pairs, cvq);
+
+ peer = s->nc.peer;
+ for (int i = 0; i < data_queue_pairs + cvq; i++) {
+ VhostVDPAState *vdpa_state;
+ NetClientState *nc;
+
+ if (i < data_queue_pairs) {
+ nc = qemu_get_peer(peer, i);
+ } else {
+ nc = qemu_get_peer(peer, n->max_queue_pairs);
+ }
+
+ vdpa_state = DO_UPCAST(VhostVDPAState, nc, nc);
+ vdpa_state->vhost_vdpa.shadow_data = enable;
+
+ if (i < data_queue_pairs) {
+ /* Do not override CVQ shadow_vqs_enabled */
+ vdpa_state->vhost_vdpa.shadow_vqs_enabled = enable;
+ }
+ }
+
+ r = vhost_net_start(vdev, n->nic->ncs, data_queue_pairs, cvq);
+ if (unlikely(r < 0)) {
+ error_report("unable to start vhost net: %s(%d)", g_strerror(-r), -r);
+ }
+}
+
+static void vdpa_net_migration_state_notifier(Notifier *notifier, void *data)
+{
+ MigrationState *migration = data;
+ VhostVDPAState *s = container_of(notifier, VhostVDPAState,
+ migration_state);
+
+ if (migration_in_setup(migration)) {
+ vhost_vdpa_net_log_global_enable(s, true);
+ } else if (migration_has_failed(migration)) {
+ vhost_vdpa_net_log_global_enable(s, false);
+ }
+}
+
static void vhost_vdpa_net_data_start_first(VhostVDPAState *s)
{
struct vhost_vdpa *v = &s->vhost_vdpa;
+ add_migration_state_change_notifier(&s->migration_state);
if (v->shadow_vqs_enabled) {
v->iova_tree = vhost_iova_tree_new(v->iova_range.first,
v->iova_range.last);
@@ -258,6 +330,15 @@ static int vhost_vdpa_net_data_start(NetClientState *nc)
assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
+ if (s->always_svq ||
+ migration_is_setup_or_active(migrate_get_current()->state)) {
+ v->shadow_vqs_enabled = true;
+ v->shadow_data = true;
+ } else {
+ v->shadow_vqs_enabled = false;
+ v->shadow_data = false;
+ }
+
if (v->index == 0) {
vhost_vdpa_net_data_start_first(s);
return 0;
@@ -278,6 +359,10 @@ static void vhost_vdpa_net_client_stop(NetClientState *nc)
assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
+ if (s->vhost_vdpa.index == 0) {
+ remove_migration_state_change_notifier(&s->migration_state);
+ }
+
dev = s->vhost_vdpa.dev;
if (dev->vq_index + dev->nvqs == dev->vq_index_end) {
g_clear_pointer(&s->vhost_vdpa.iova_tree, vhost_iova_tree_delete);
@@ -741,6 +826,7 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
s->vhost_vdpa.device_fd = vdpa_device_fd;
s->vhost_vdpa.index = queue_pair_index;
s->always_svq = svq;
+ s->migration_state.notify = vdpa_net_migration_state_notifier;
s->vhost_vdpa.shadow_vqs_enabled = svq;
s->vhost_vdpa.iova_range = iova_range;
s->vhost_vdpa.shadow_data = svq;
This allows net to restart the device backend to configure SVQ on it. Ideally, these changes should not be net specific. However, the vdpa net backend is the one with enough knowledge to configure everything because of some reasons: * Queues might need to be shadowed or not depending on its kind (control vs data). * Queues need to share the same map translations (iova tree). Because of that it is cleaner to restart the whole net backend and configure again as expected, similar to how vhost-kernel moves between userspace and passthrough. If more kinds of devices need dynamic switching to SVQ we can create a callback struct like VhostOps and move most of the code there. VhostOps cannot be reused since all vdpa backend share them, and to personalize just for networking would be too heavy. Signed-off-by: Eugenio Pérez <eperezma@redhat.com> --- v3: * Check for migration state at vdpa device start to enable SVQ in data vqs. v1 from RFC: * Add TODO to use the resume operation in the future. * Use migration_in_setup and migration_has_failed instead of a complicated switch case. --- net/vhost-vdpa.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+)