#include "qapi/qmp/qjson.h"
#include "qapi-event.h"
#include "hw/virtio/virtio-access.h"
+#include "migration/misc.h"
#define VIRTIO_NET_VM_VERSION 11
/* previously fixed value */
#define VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE 256
+#define VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE 256
+
/* for now, only allow larger queues; with virtio-1, guest can downsize */
#define VIRTIO_NET_RX_QUEUE_MIN_SIZE VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE
+#define VIRTIO_NET_TX_QUEUE_MIN_SIZE VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE
/*
* Calculate the number of bytes up to and including the given 'field' of
}
}
+static int virtio_net_max_tx_queue_size(VirtIONet *n)
+{
+ NetClientState *peer = n->nic_conf.peers.ncs[0];
+
+ /*
+ * Backends other than vhost-user don't support max queue size.
+ */
+ if (!peer) {
+ return VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE;
+ }
+
+ if (peer->info->type != NET_CLIENT_DRIVER_VHOST_USER) {
+ return VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE;
+ }
+
+ return VIRTQUEUE_MAX_SIZE;
+}
+
static int peer_attach(VirtIONet *n, int index)
{
NetClientState *nc = qemu_get_subqueue(n->nic, index);
return 0;
}
+ if (n->max_queues == 1) {
+ return 0;
+ }
+
return tap_enable(nc->peer);
}
if (!get_vhost_net(nc->peer)) {
return features;
}
- return vhost_net_get_features(get_vhost_net(nc->peer), features);
+ features = vhost_net_get_features(get_vhost_net(nc->peer), features);
+ vdev->backend_features = features;
+
+ if (n->mtu_bypass_backend &&
+ (n->host_features & 1ULL << VIRTIO_NET_F_MTU)) {
+ features |= (1ULL << VIRTIO_NET_F_MTU);
+ }
+
+ return features;
}
static uint64_t virtio_net_bad_features(VirtIODevice *vdev)
VirtIONet *n = VIRTIO_NET(vdev);
int i;
+ if (n->mtu_bypass_backend &&
+ !virtio_has_feature(vdev->backend_features, VIRTIO_NET_F_MTU)) {
+ features &= ~(1ULL << VIRTIO_NET_F_MTU);
+ }
+
virtio_net_set_multiqueue(n,
virtio_has_feature(features, VIRTIO_NET_F_MQ));
return 0;
}
-static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, size_t size)
+static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
+ size_t size)
{
VirtIONet *n = qemu_get_nic_opaque(nc);
VirtIONetQueue *q = virtio_net_get_subqueue(nc);
return size;
}
+static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf,
+ size_t size)
+{
+ ssize_t r;
+
+ rcu_read_lock();
+ r = virtio_net_receive_rcu(nc, buf, size);
+ rcu_read_unlock();
+ return r;
+}
+
static int32_t virtio_net_flush_tx(VirtIONetQueue *q);
static void virtio_net_tx_complete(NetClientState *nc, ssize_t len)
n->vqs[index].rx_vq = virtio_add_queue(vdev, n->net_conf.rx_queue_size,
virtio_net_handle_rx);
+
if (n->net_conf.tx && !strcmp(n->net_conf.tx, "timer")) {
n->vqs[index].tx_vq =
- virtio_add_queue(vdev, 256, virtio_net_handle_tx_timer);
+ virtio_add_queue(vdev, n->net_conf.tx_queue_size,
+ virtio_net_handle_tx_timer);
n->vqs[index].tx_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
virtio_net_tx_timer,
&n->vqs[index]);
} else {
n->vqs[index].tx_vq =
- virtio_add_queue(vdev, 256, virtio_net_handle_tx_bh);
+ virtio_add_queue(vdev, n->net_conf.tx_queue_size,
+ virtio_net_handle_tx_bh);
n->vqs[index].tx_bh = qemu_bh_new(virtio_net_tx_bh, &n->vqs[index]);
}
if (q->tx_timer) {
timer_del(q->tx_timer);
timer_free(q->tx_timer);
+ q->tx_timer = NULL;
} else {
qemu_bh_delete(q->tx_bh);
+ q->tx_bh = NULL;
}
+ q->tx_waiting = 0;
virtio_del_queue(vdev, index * 2 + 1);
}
virtio_net_set_queues(n);
}
-static void virtio_net_save_device(VirtIODevice *vdev, QEMUFile *f)
+static int virtio_net_post_load_device(void *opaque, int version_id)
{
- VirtIONet *n = VIRTIO_NET(vdev);
- int i;
-
- qemu_put_buffer(f, n->mac, ETH_ALEN);
- qemu_put_be32(f, n->vqs[0].tx_waiting);
- qemu_put_be32(f, n->mergeable_rx_bufs);
- qemu_put_be16(f, n->status);
- qemu_put_byte(f, n->promisc);
- qemu_put_byte(f, n->allmulti);
- qemu_put_be32(f, n->mac_table.in_use);
- qemu_put_buffer(f, n->mac_table.macs, n->mac_table.in_use * ETH_ALEN);
- qemu_put_buffer(f, (uint8_t *)n->vlans, MAX_VLAN >> 3);
- qemu_put_be32(f, n->has_vnet_hdr);
- qemu_put_byte(f, n->mac_table.multi_overflow);
- qemu_put_byte(f, n->mac_table.uni_overflow);
- qemu_put_byte(f, n->alluni);
- qemu_put_byte(f, n->nomulti);
- qemu_put_byte(f, n->nouni);
- qemu_put_byte(f, n->nobcast);
- qemu_put_byte(f, n->has_ufo);
- if (n->max_queues > 1) {
- qemu_put_be16(f, n->max_queues);
- qemu_put_be16(f, n->curr_queues);
- for (i = 1; i < n->curr_queues; i++) {
- qemu_put_be32(f, n->vqs[i].tx_waiting);
- }
- }
-
- if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) {
- qemu_put_be64(f, n->curr_guest_offloads);
- }
-}
-
-static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f,
- int version_id)
-{
- VirtIONet *n = VIRTIO_NET(vdev);
+ VirtIONet *n = opaque;
+ VirtIODevice *vdev = VIRTIO_DEVICE(n);
int i, link_down;
- qemu_get_buffer(f, n->mac, ETH_ALEN);
- n->vqs[0].tx_waiting = qemu_get_be32(f);
-
- virtio_net_set_mrg_rx_bufs(n, qemu_get_be32(f),
+ virtio_net_set_mrg_rx_bufs(n, n->mergeable_rx_bufs,
virtio_vdev_has_feature(vdev,
VIRTIO_F_VERSION_1));
- n->status = qemu_get_be16(f);
-
- n->promisc = qemu_get_byte(f);
- n->allmulti = qemu_get_byte(f);
-
- n->mac_table.in_use = qemu_get_be32(f);
/* MAC_TABLE_ENTRIES may be different from the saved image */
- if (n->mac_table.in_use <= MAC_TABLE_ENTRIES) {
- qemu_get_buffer(f, n->mac_table.macs,
- n->mac_table.in_use * ETH_ALEN);
- } else {
- int64_t i;
-
- /* Overflow detected - can happen if source has a larger MAC table.
- * We simply set overflow flag so there's no need to maintain the
- * table of addresses, discard them all.
- * Note: 64 bit math to avoid integer overflow.
- */
- for (i = 0; i < (int64_t)n->mac_table.in_use * ETH_ALEN; ++i) {
- qemu_get_byte(f);
- }
- n->mac_table.multi_overflow = n->mac_table.uni_overflow = 1;
+ if (n->mac_table.in_use > MAC_TABLE_ENTRIES) {
n->mac_table.in_use = 0;
}
-
- qemu_get_buffer(f, (uint8_t *)n->vlans, MAX_VLAN >> 3);
-
- if (qemu_get_be32(f) && !peer_has_vnet_hdr(n)) {
- error_report("virtio-net: saved image requires vnet_hdr=on");
- return -1;
- }
-
- n->mac_table.multi_overflow = qemu_get_byte(f);
- n->mac_table.uni_overflow = qemu_get_byte(f);
-
- n->alluni = qemu_get_byte(f);
- n->nomulti = qemu_get_byte(f);
- n->nouni = qemu_get_byte(f);
- n->nobcast = qemu_get_byte(f);
-
- if (qemu_get_byte(f) && !peer_has_ufo(n)) {
- error_report("virtio-net: saved image requires TUN_F_UFO support");
- return -1;
- }
-
- if (n->max_queues > 1) {
- if (n->max_queues != qemu_get_be16(f)) {
- error_report("virtio-net: different max_queues ");
- return -1;
- }
-
- n->curr_queues = qemu_get_be16(f);
- if (n->curr_queues > n->max_queues) {
- error_report("virtio-net: curr_queues %x > max_queues %x",
- n->curr_queues, n->max_queues);
- return -1;
- }
- for (i = 1; i < n->curr_queues; i++) {
- n->vqs[i].tx_waiting = qemu_get_be32(f);
- }
- }
- if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) {
- n->curr_guest_offloads = qemu_get_be64(f);
- } else {
+ if (!virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) {
n->curr_guest_offloads = virtio_net_supported_guest_offloads(n);
}
return 0;
}
+/* tx_waiting field of a VirtIONetQueue */
+static const VMStateDescription vmstate_virtio_net_queue_tx_waiting = {
+ .name = "virtio-net-queue-tx_waiting",
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT32(tx_waiting, VirtIONetQueue),
+ VMSTATE_END_OF_LIST()
+ },
+};
+
+static bool max_queues_gt_1(void *opaque, int version_id)
+{
+ return VIRTIO_NET(opaque)->max_queues > 1;
+}
+
+static bool has_ctrl_guest_offloads(void *opaque, int version_id)
+{
+ return virtio_vdev_has_feature(VIRTIO_DEVICE(opaque),
+ VIRTIO_NET_F_CTRL_GUEST_OFFLOADS);
+}
+
+static bool mac_table_fits(void *opaque, int version_id)
+{
+ return VIRTIO_NET(opaque)->mac_table.in_use <= MAC_TABLE_ENTRIES;
+}
+
+static bool mac_table_doesnt_fit(void *opaque, int version_id)
+{
+ return !mac_table_fits(opaque, version_id);
+}
+
+/* This temporary type is shared by all the WITH_TMP methods
+ * although only some fields are used by each.
+ */
+struct VirtIONetMigTmp {
+ VirtIONet *parent;
+ VirtIONetQueue *vqs_1;
+ uint16_t curr_queues_1;
+ uint8_t has_ufo;
+ uint32_t has_vnet_hdr;
+};
+
+/* The 2nd and subsequent tx_waiting flags are loaded later than
+ * the 1st entry in the queues and only if there's more than one
+ * entry. We use the tmp mechanism to calculate a temporary
+ * pointer and count and also validate the count.
+ */
+
+static void virtio_net_tx_waiting_pre_save(void *opaque)
+{
+ struct VirtIONetMigTmp *tmp = opaque;
+
+ tmp->vqs_1 = tmp->parent->vqs + 1;
+ tmp->curr_queues_1 = tmp->parent->curr_queues - 1;
+ if (tmp->parent->curr_queues == 0) {
+ tmp->curr_queues_1 = 0;
+ }
+}
+
+static int virtio_net_tx_waiting_pre_load(void *opaque)
+{
+ struct VirtIONetMigTmp *tmp = opaque;
+
+ /* Reuse the pointer setup from save */
+ virtio_net_tx_waiting_pre_save(opaque);
+
+ if (tmp->parent->curr_queues > tmp->parent->max_queues) {
+ error_report("virtio-net: curr_queues %x > max_queues %x",
+ tmp->parent->curr_queues, tmp->parent->max_queues);
+
+ return -EINVAL;
+ }
+
+ return 0; /* all good */
+}
+
+static const VMStateDescription vmstate_virtio_net_tx_waiting = {
+ .name = "virtio-net-tx_waiting",
+ .pre_load = virtio_net_tx_waiting_pre_load,
+ .pre_save = virtio_net_tx_waiting_pre_save,
+ .fields = (VMStateField[]) {
+ VMSTATE_STRUCT_VARRAY_POINTER_UINT16(vqs_1, struct VirtIONetMigTmp,
+ curr_queues_1,
+ vmstate_virtio_net_queue_tx_waiting,
+ struct VirtIONetQueue),
+ VMSTATE_END_OF_LIST()
+ },
+};
+
+/* the 'has_ufo' flag is just tested; if the incoming stream has the
+ * flag set we need to check that we have it
+ */
+static int virtio_net_ufo_post_load(void *opaque, int version_id)
+{
+ struct VirtIONetMigTmp *tmp = opaque;
+
+ if (tmp->has_ufo && !peer_has_ufo(tmp->parent)) {
+ error_report("virtio-net: saved image requires TUN_F_UFO support");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void virtio_net_ufo_pre_save(void *opaque)
+{
+ struct VirtIONetMigTmp *tmp = opaque;
+
+ tmp->has_ufo = tmp->parent->has_ufo;
+}
+
+static const VMStateDescription vmstate_virtio_net_has_ufo = {
+ .name = "virtio-net-ufo",
+ .post_load = virtio_net_ufo_post_load,
+ .pre_save = virtio_net_ufo_pre_save,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT8(has_ufo, struct VirtIONetMigTmp),
+ VMSTATE_END_OF_LIST()
+ },
+};
+
+/* the 'has_vnet_hdr' flag is just tested; if the incoming stream has the
+ * flag set we need to check that we have it
+ */
+static int virtio_net_vnet_post_load(void *opaque, int version_id)
+{
+ struct VirtIONetMigTmp *tmp = opaque;
+
+ if (tmp->has_vnet_hdr && !peer_has_vnet_hdr(tmp->parent)) {
+ error_report("virtio-net: saved image requires vnet_hdr=on");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void virtio_net_vnet_pre_save(void *opaque)
+{
+ struct VirtIONetMigTmp *tmp = opaque;
+
+ tmp->has_vnet_hdr = tmp->parent->has_vnet_hdr;
+}
+
+static const VMStateDescription vmstate_virtio_net_has_vnet = {
+ .name = "virtio-net-vnet",
+ .post_load = virtio_net_vnet_post_load,
+ .pre_save = virtio_net_vnet_pre_save,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT32(has_vnet_hdr, struct VirtIONetMigTmp),
+ VMSTATE_END_OF_LIST()
+ },
+};
+
+static const VMStateDescription vmstate_virtio_net_device = {
+ .name = "virtio-net-device",
+ .version_id = VIRTIO_NET_VM_VERSION,
+ .minimum_version_id = VIRTIO_NET_VM_VERSION,
+ .post_load = virtio_net_post_load_device,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT8_ARRAY(mac, VirtIONet, ETH_ALEN),
+ VMSTATE_STRUCT_POINTER(vqs, VirtIONet,
+ vmstate_virtio_net_queue_tx_waiting,
+ VirtIONetQueue),
+ VMSTATE_UINT32(mergeable_rx_bufs, VirtIONet),
+ VMSTATE_UINT16(status, VirtIONet),
+ VMSTATE_UINT8(promisc, VirtIONet),
+ VMSTATE_UINT8(allmulti, VirtIONet),
+ VMSTATE_UINT32(mac_table.in_use, VirtIONet),
+
+ /* Guarded pair: If it fits we load it, else we throw it away
+ * - can happen if source has a larger MAC table.; post-load
+ * sets flags in this case.
+ */
+ VMSTATE_VBUFFER_MULTIPLY(mac_table.macs, VirtIONet,
+ 0, mac_table_fits, mac_table.in_use,
+ ETH_ALEN),
+ VMSTATE_UNUSED_VARRAY_UINT32(VirtIONet, mac_table_doesnt_fit, 0,
+ mac_table.in_use, ETH_ALEN),
+
+ /* Note: This is an array of uint32's that's always been saved as a
+ * buffer; hold onto your endiannesses; it's actually used as a bitmap
+ * but based on the uint.
+ */
+ VMSTATE_BUFFER_POINTER_UNSAFE(vlans, VirtIONet, 0, MAX_VLAN >> 3),
+ VMSTATE_WITH_TMP(VirtIONet, struct VirtIONetMigTmp,
+ vmstate_virtio_net_has_vnet),
+ VMSTATE_UINT8(mac_table.multi_overflow, VirtIONet),
+ VMSTATE_UINT8(mac_table.uni_overflow, VirtIONet),
+ VMSTATE_UINT8(alluni, VirtIONet),
+ VMSTATE_UINT8(nomulti, VirtIONet),
+ VMSTATE_UINT8(nouni, VirtIONet),
+ VMSTATE_UINT8(nobcast, VirtIONet),
+ VMSTATE_WITH_TMP(VirtIONet, struct VirtIONetMigTmp,
+ vmstate_virtio_net_has_ufo),
+ VMSTATE_SINGLE_TEST(max_queues, VirtIONet, max_queues_gt_1, 0,
+ vmstate_info_uint16_equal, uint16_t),
+ VMSTATE_UINT16_TEST(curr_queues, VirtIONet, max_queues_gt_1),
+ VMSTATE_WITH_TMP(VirtIONet, struct VirtIONetMigTmp,
+ vmstate_virtio_net_tx_waiting),
+ VMSTATE_UINT64_TEST(curr_guest_offloads, VirtIONet,
+ has_ctrl_guest_offloads),
+ VMSTATE_END_OF_LIST()
+ },
+};
+
static NetClientInfo net_virtio_info = {
.type = NET_CLIENT_DRIVER_NIC,
.size = sizeof(NICState),
*/
if (n->net_conf.rx_queue_size < VIRTIO_NET_RX_QUEUE_MIN_SIZE ||
n->net_conf.rx_queue_size > VIRTQUEUE_MAX_SIZE ||
- (n->net_conf.rx_queue_size & (n->net_conf.rx_queue_size - 1))) {
+ !is_power_of_2(n->net_conf.rx_queue_size)) {
error_setg(errp, "Invalid rx_queue_size (= %" PRIu16 "), "
"must be a power of 2 between %d and %d.",
n->net_conf.rx_queue_size, VIRTIO_NET_RX_QUEUE_MIN_SIZE,
return;
}
+ if (n->net_conf.tx_queue_size < VIRTIO_NET_TX_QUEUE_MIN_SIZE ||
+ n->net_conf.tx_queue_size > VIRTQUEUE_MAX_SIZE ||
+ !is_power_of_2(n->net_conf.tx_queue_size)) {
+ error_setg(errp, "Invalid tx_queue_size (= %" PRIu16 "), "
+ "must be a power of 2 between %d and %d",
+ n->net_conf.tx_queue_size, VIRTIO_NET_TX_QUEUE_MIN_SIZE,
+ VIRTQUEUE_MAX_SIZE);
+ virtio_cleanup(vdev);
+ return;
+ }
+
n->max_queues = MAX(n->nic_conf.peers.queues, 1);
if (n->max_queues * 2 + 1 > VIRTIO_QUEUE_MAX) {
error_setg(errp, "Invalid number of queues (= %" PRIu32 "), "
error_report("Defaulting to \"bh\"");
}
+ n->net_conf.tx_queue_size = MIN(virtio_net_max_tx_queue_size(n),
+ n->net_conf.tx_queue_size);
+
for (i = 0; i < n->max_queues; i++) {
virtio_net_add_queue(n, i);
}
DEFINE_PROP_STRING("tx", VirtIONet, net_conf.tx),
DEFINE_PROP_UINT16("rx_queue_size", VirtIONet, net_conf.rx_queue_size,
VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE),
+ DEFINE_PROP_UINT16("tx_queue_size", VirtIONet, net_conf.tx_queue_size,
+ VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE),
DEFINE_PROP_UINT16("host_mtu", VirtIONet, net_conf.mtu, 0),
+ DEFINE_PROP_BOOL("x-mtu-bypass-backend", VirtIONet, mtu_bypass_backend,
+ true),
DEFINE_PROP_END_OF_LIST(),
};
vdc->set_status = virtio_net_set_status;
vdc->guest_notifier_mask = virtio_net_guest_notifier_mask;
vdc->guest_notifier_pending = virtio_net_guest_notifier_pending;
- vdc->load = virtio_net_load_device;
- vdc->save = virtio_net_save_device;
vdc->legacy_features |= (0x1 << VIRTIO_NET_F_GSO);
+ vdc->vmsd = &vmstate_virtio_net_device;
}
static const TypeInfo virtio_net_info = {
projects / qemu.git / blobdiff