On Sun, Oct 18, 2026 at 12:52:31AM +0530, Koushik Dutta wrote: > Implement notification coalescing to reduce interrupt overhead. > Guests configure time-based (microseconds) or count-based (packets) > coalescing via ethtool -C. Coalescing state is migrated via VMState > for live migration support. > > Note: Coalescing is disabled when tx=timer is configured, as timer > mode already provides packet batching. > > Performance impact: 20% reduction in CPU overhead, 30% fewer interrupts > under moderate coalescing settings. > > Signed-off-by: Koushik Dutta <[email protected]> > --- > hw/net/virtio-net.c | 199 ++++++++++++++++++++++++++++++++- > include/hw/virtio/virtio-net.h | 10 ++ > net/passt.c | 1 + > net/tap.c | 1 + > net/vhost-user.c | 1 + > net/vhost-vdpa.c | 1 + > 6 files changed, 209 insertions(+), 4 deletions(-) > > diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c > index 5ca011f890..610cc2b580 100644 > --- a/hw/net/virtio-net.c > +++ b/hw/net/virtio-net.c > @@ -158,6 +158,16 @@ static void flush_or_purge_queued_packets(NetClientState > *nc) > * - we could suppress RX interrupt if we were so inclined. > */ > > +static void virtio_net_rx_notify(void *opaque) > +{ > + VirtIONetQueue *q = opaque; > + VirtIONet *n = q->n; > + VirtIODevice *vdev = VIRTIO_DEVICE(n); > + > + q->rx_coal.pkt_cnt = 0; > + virtio_notify(vdev, q->rx_vq); > +} > + > static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) > { > VirtIONet *n = VIRTIO_NET(vdev); > @@ -1003,6 +1013,90 @@ static void virtio_net_set_features(VirtIODevice *vdev, > } > } > > +static void virtio_net_tx_notification_timer(void *opaque) > +{ > + VirtIONetQueue *q = opaque; > + VirtIONet *n = q->n; > + VirtIODevice *vdev = VIRTIO_DEVICE(n); > + > + q->tx_coal.pkt_cnt = 0; > + virtio_notify(vdev, q->tx_vq); > +} > + > +static bool virtio_net_tx_should_notify(VirtIONetQueue *q) > +{ > + if (!q->tx_coal.timer) { > + return true; > + } > + > + q->tx_coal.pkt_cnt++; > + > + if (q->tx_coal.packets > 0 && q->tx_coal.pkt_cnt >= q->tx_coal.packets) { > + q->tx_coal.pkt_cnt = 0; > + timer_del(q->tx_coal.timer); > + return true; > + } > + > + if (!timer_pending(q->tx_coal.timer)) { > + timer_mod(q->tx_coal.timer, > + qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + > + q->tx_coal.usecs * 1000); > + } > + > + return false; > +} > + > +static int virtio_net_handle_coal(VirtIONet *n, uint8_t cmd, > + struct iovec *iov, unsigned int iov_cnt) > +{ > + struct virtio_net_ctrl_coal coal; > + VirtIONetQueue *q; > + size_t s; > + int i; > + > + if (n->tx_timer_activate) { > + return VIRTIO_NET_ERR; > + } > + > + s = iov_to_buf(iov, iov_cnt, 0, &coal, sizeof(coal)); > + if (s != sizeof(coal)) { > + return VIRTIO_NET_ERR; > + } > + > + if (cmd == VIRTIO_NET_CTRL_NOTF_COAL_RX_SET) { > + for (i = 0; i < n->max_queue_pairs; i++) { > + q = &n->vqs[i]; > + q->rx_coal.usecs = le32_to_cpu(coal.max_usecs); > + q->rx_coal.packets = le32_to_cpu(coal.max_packets); > + q->rx_coal.pkt_cnt = 0; > + if (q->rx_coal.usecs > 0) { > + g_clear_pointer(&q->rx_coal.timer, timer_free); > + q->rx_coal.timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, > + virtio_net_rx_notify, > + q); > + } else { > + g_clear_pointer(&q->rx_coal.timer, timer_free); > + } > + } > + } else if (cmd == VIRTIO_NET_CTRL_NOTF_COAL_TX_SET) { > + for (i = 0; i < n->max_queue_pairs; i++) { > + q = &n->vqs[i]; > + q->tx_coal.usecs = le32_to_cpu(coal.max_usecs); > + q->tx_coal.packets = le32_to_cpu(coal.max_packets); > + q->tx_coal.pkt_cnt = 0; > + if (q->tx_coal.usecs > 0) { > + g_clear_pointer(&q->tx_coal.timer, timer_free); > + q->tx_coal.timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, > + > virtio_net_tx_notification_timer, > + q); > + } else { > + g_clear_pointer(&q->tx_coal.timer, timer_free); > + } > + } > + } > + return VIRTIO_NET_OK; > +} > + > static int virtio_net_handle_rx_mode(VirtIONet *n, uint8_t cmd, > struct iovec *iov, unsigned int iov_cnt) > { > @@ -1582,6 +1676,8 @@ size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev, > status = virtio_net_handle_mq(n, ctrl.cmd, iov, out_num); > } else if (ctrl.class == VIRTIO_NET_CTRL_GUEST_OFFLOADS) { > status = virtio_net_handle_offloads(n, ctrl.cmd, iov, out_num); > + } else if (ctrl.class == VIRTIO_NET_CTRL_NOTF_COAL) { > + status = virtio_net_handle_coal(n, ctrl.cmd, iov, out_num); > } > > s = iov_from_buf(in_sg, in_num, 0, &status, sizeof(status)); > @@ -2056,7 +2152,23 @@ static ssize_t virtio_net_receive_rcu(NetClientState > *nc, const uint8_t *buf, > } > > virtqueue_flush(q->rx_vq, i); > - virtio_notify(vdev, q->rx_vq); > + > + /* rx coalescing */ > + q->rx_coal.pkt_cnt += i; > + if (q->rx_coal.usecs == 0 || q->rx_coal.pkt_cnt >= q->rx_coal.packets) { > + if (q->rx_coal.timer) { > + timer_del(q->rx_coal.timer); > + } > + virtio_net_rx_notify(q); > + } else { > + if (q->rx_coal.timer) { > + if (!timer_pending(q->rx_coal.timer)) { > + timer_mod(q->rx_coal.timer, > + qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + > + q->rx_coal.usecs * 1000); /* Converted to ns */ > + } > + } > + } > > return size; > > @@ -2739,7 +2851,9 @@ static void virtio_net_tx_complete(NetClientState *nc, > ssize_t len) > int ret; > > virtqueue_push(q->tx_vq, q->async_tx.elem, 0); > - virtio_notify(vdev, q->tx_vq); > + if (virtio_net_tx_should_notify(q)) { > + virtio_notify(vdev, q->tx_vq); > + } > > g_free(q->async_tx.elem); > q->async_tx.elem = NULL; > @@ -2851,7 +2965,10 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q) > > drop: > virtqueue_push(q->tx_vq, elem, 0); > - virtio_notify(vdev, q->tx_vq); > + if (virtio_net_tx_should_notify(q)) { > + virtio_notify(vdev, q->tx_vq); > + } > + > g_free(elem); > > if (++num_packets >= n->tx_burst) { > @@ -3054,6 +3171,12 @@ static void virtio_net_add_queue(VirtIONet *n, int > index) > &DEVICE(vdev)->mem_reentrancy_guard); > > n->vqs[index].tx_waiting = 0; > + n->vqs[index].rx_coal.pkt_cnt = 0; > + n->vqs[index].tx_coal.pkt_cnt = 0; > + n->vqs[index].rx_coal.usecs = 0; > + n->vqs[index].tx_coal.usecs = 0; > + n->vqs[index].rx_coal.packets = 0; > + n->vqs[index].tx_coal.packets = 0; > n->vqs[index].n = n; > } > > @@ -3066,6 +3189,10 @@ static void virtio_net_del_queue(VirtIONet *n, int > index) > qemu_purge_queued_packets(nc); > > virtio_del_queue(vdev, index * 2); > + > + g_clear_pointer(&q->rx_coal.timer, timer_free); > + g_clear_pointer(&q->tx_coal.timer, timer_free); > + > if (q->tx_timer) { > timer_free(q->tx_timer); > q->tx_timer = NULL; > @@ -3156,6 +3283,13 @@ static void virtio_net_get_features(VirtIODevice > *vdev, uint64_t *features, > virtio_features_or(features, features, n->host_features_ex); > > virtio_add_feature_ex(features, VIRTIO_NET_F_MAC); > + if (n->tx_timer_activate) { > + virtio_clear_feature_ex(features, VIRTIO_NET_F_NOTF_COAL); > + } else { > + if (!virtio_has_feature(*features, VIRTIO_NET_F_NOTF_COAL)) { > + *features &= ~(1ULL << VIRTIO_NET_F_NOTF_COAL); > + } > + } > > if (n->peers_wait_incoming) { > /* > @@ -3336,6 +3470,21 @@ static int virtio_net_post_load_device(void *opaque, > int version_id) > return -EINVAL; > } > > + for (i = 0; i < n->max_queue_pairs; i++) { > + VirtIONetQueue *q = &n->vqs[i]; > + if (q->rx_coal.usecs > 0 && !q->rx_coal.timer) { > + q->rx_coal.timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, > + virtio_net_rx_notify, > + q); > + } > + > + if (q->tx_coal.usecs > 0 && !q->tx_coal.timer) { > + q->tx_coal.timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, > + virtio_net_tx_notification_timer, > + q); > + } > + } > + > return 0; > } > > @@ -3355,13 +3504,49 @@ static int virtio_net_post_load_virtio(VirtIODevice > *vdev) > return 0; > } > > +static const VMStateDescription vmstate_virtio_net_coal = { > + .name = "virtio-net-coal", > + .version_id = 1, > + .minimum_version_id = 1, > + .fields = (const VMStateField[]) { > + VMSTATE_UINT32(usecs, VirtIONetCoal), > + VMSTATE_UINT32(packets, VirtIONetCoal), > + VMSTATE_UINT32(pkt_cnt, VirtIONetCoal), > + VMSTATE_END_OF_LIST() > + }, > +}; > + > +static bool virtio_net_queue_notf_coal_needed(void *opaque) > +{ > + VirtIONetQueue *q = opaque; > + return q->rx_coal.usecs > 0 || q->tx_coal.usecs > 0; > +} > + > +static const VMStateDescription vmstate_virtio_net_queue_notf_coal = { > + .name = "virtio-net-queue-tx_waiting/notf-coal", > + .version_id = 1, > + .minimum_version_id = 1, > + .needed = virtio_net_queue_notf_coal_needed, > + .fields = (const VMStateField[]) { > + VMSTATE_STRUCT(rx_coal, VirtIONetQueue, 0, > + vmstate_virtio_net_coal, VirtIONetCoal), > + VMSTATE_STRUCT(tx_coal, VirtIONetQueue, 0, > + vmstate_virtio_net_coal, VirtIONetCoal), > + VMSTATE_END_OF_LIST() > + }, > +}; > + > /* tx_waiting field of a VirtIONetQueue */ > static const VMStateDescription vmstate_virtio_net_queue_tx_waiting = { > .name = "virtio-net-queue-tx_waiting", > .fields = (const VMStateField[]) { > VMSTATE_UINT32(tx_waiting, VirtIONetQueue), > VMSTATE_END_OF_LIST() > - }, > + }, > + .subsections = (const VMStateDescription * const []) { > + &vmstate_virtio_net_queue_notf_coal, > + NULL > + } > }; > > static bool max_queue_pairs_gt_1(void *opaque, int version_id) > @@ -4117,6 +4302,10 @@ static void virtio_net_device_realize(DeviceState > *dev, Error **errp) > > if (n->net_conf.tx && strcmp(n->net_conf.tx, "timer") == 0) { > n->tx_timer_activate = true; > + if (n->host_features & (1ULL << VIRTIO_NET_F_NOTF_COAL)) { > + warn_report("virtio-net: 'vq_notf_coal' is incompatible with > 'tx=timer'," > + "disabling notification coalescing"); > + } > } > > n->net_conf.tx_queue_size = MIN(virtio_net_max_tx_queue_size(n), > @@ -4413,6 +4602,8 @@ static const Property virtio_net_properties[] = { > VIRTIO_NET_F_GUEST_USO6, true), > DEFINE_PROP_BIT64("host_uso", VirtIONet, host_features, > VIRTIO_NET_F_HOST_USO, true), > + DEFINE_PROP_BIT64("vq_notf_coal", VirtIONet, host_features, > + VIRTIO_NET_F_NOTF_COAL, false), > DEFINE_PROP_ON_OFF_AUTO_BIT64("hash-ipv4", VirtIONet, > rss_data.specified_hash_types, > VIRTIO_NET_HASH_REPORT_IPv4 - 1, > diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h > index 2e7bc29967..c7bb61b3e5 100644 > --- a/include/hw/virtio/virtio-net.h > +++ b/include/hw/virtio/virtio-net.h > @@ -155,6 +155,14 @@ typedef struct VirtioNetRssData { > uint16_t default_queue; > } VirtioNetRssData; > > +/* Interrupt notification coalescing parameters */ > +typedef struct VirtIONetCoal { > + uint32_t usecs; /* Timeout in microseconds */ > + uint32_t packets; /* Packet count threshold */ > + uint32_t pkt_cnt; /* Current packet count since last notification */ > + QEMUTimer *timer; /* Coalescing timer */ > +} VirtIONetCoal; > + > typedef struct VirtIONetQueue { > VirtQueue *rx_vq; > VirtQueue *tx_vq; > @@ -165,6 +173,8 @@ typedef struct VirtIONetQueue { > VirtQueueElement *elem; > } async_tx; > struct VirtIONet *n; > + VirtIONetCoal rx_coal; > + VirtIONetCoal tx_coal; > } VirtIONetQueue; > > struct VirtIONet { > diff --git a/net/passt.c b/net/passt.c > index e65198960e..5ce25d0463 100644 > --- a/net/passt.c > +++ b/net/passt.c > @@ -52,6 +52,7 @@ static const int user_feature_bits[] = { > VIRTIO_NET_F_GUEST_USO4, > VIRTIO_NET_F_GUEST_USO6, > VIRTIO_NET_F_HOST_USO, > + VIRTIO_NET_F_NOTF_COAL, > > /* This bit implies RARP isn't sent by QEMU out of band */ > VIRTIO_NET_F_GUEST_ANNOUNCE, > diff --git a/net/tap.c b/net/tap.c > index d71e3dd117..59286e141d 100644 > --- a/net/tap.c > +++ b/net/tap.c > @@ -69,6 +69,7 @@ static const int kernel_feature_bits[] = { > VIRTIO_F_NOTIFICATION_DATA, > VIRTIO_NET_F_RSC_EXT, > VIRTIO_NET_F_HASH_REPORT, > + VIRTIO_NET_F_NOTF_COAL, > VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO, > VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO, > VHOST_INVALID_FEATURE_BIT > diff --git a/net/vhost-user.c b/net/vhost-user.c > index b849de92da..4674ebb5b5 100644 > --- a/net/vhost-user.c > +++ b/net/vhost-user.c > @@ -54,6 +54,7 @@ static const int user_feature_bits[] = { > VIRTIO_NET_F_GUEST_USO4, > VIRTIO_NET_F_GUEST_USO6, > VIRTIO_NET_F_HOST_USO, > + VIRTIO_NET_F_NOTF_COAL, > > /* This bit implies RARP isn't sent by QEMU out of band */ > VIRTIO_NET_F_GUEST_ANNOUNCE, > diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c > index 1052361a4a..ebd77135da 100644 > --- a/net/vhost-vdpa.c > +++ b/net/vhost-vdpa.c > @@ -71,6 +71,7 @@ static const int vdpa_feature_bits[] = { > VIRTIO_NET_F_CTRL_RX, > VIRTIO_NET_F_CTRL_RX_EXTRA, > VIRTIO_NET_F_CTRL_VLAN, > + VIRTIO_NET_F_NOTF_COAL, > VIRTIO_NET_F_CTRL_VQ, > VIRTIO_NET_F_GSO, > VIRTIO_NET_F_GUEST_CSUM,
which of these backends actually implement the feature? We do not pass-through all bits not because we like code duplication but because we never know what configuration will be required from backend. > -- > 2.53.0
