*
*/
-#include "iov.h"
-#include "virtio.h"
-#include "net.h"
+#include "qemu/iov.h"
+#include "hw/virtio.h"
+#include "net/net.h"
#include "net/checksum.h"
#include "net/tap.h"
-#include "qemu-error.h"
-#include "qemu-timer.h"
-#include "virtio-net.h"
-#include "vhost_net.h"
+#include "qemu/error-report.h"
+#include "qemu/timer.h"
+#include "hw/virtio-net.h"
+#include "hw/vhost_net.h"
#define VIRTIO_NET_VM_VERSION 11
#define MAC_TABLE_ENTRIES 64
#define MAX_VLAN (1 << 12) /* Per 802.1Q definition */
+typedef struct VirtIONetQueue {
+ VirtQueue *rx_vq;
+ VirtQueue *tx_vq;
+ QEMUTimer *tx_timer;
+ QEMUBH *tx_bh;
+ int tx_waiting;
+ struct {
+ VirtQueueElement elem;
+ ssize_t len;
+ } async_tx;
+ struct VirtIONet *n;
+} VirtIONetQueue;
+
typedef struct VirtIONet
{
VirtIODevice vdev;
uint8_t mac[ETH_ALEN];
uint16_t status;
- VirtQueue *rx_vq;
- VirtQueue *tx_vq;
+ VirtIONetQueue vqs[MAX_QUEUE_NUM];
VirtQueue *ctrl_vq;
NICState *nic;
- QEMUTimer *tx_timer;
- QEMUBH *tx_bh;
uint32_t tx_timeout;
int32_t tx_burst;
- int tx_waiting;
uint32_t has_vnet_hdr;
size_t host_hdr_len;
size_t guest_hdr_len;
uint8_t has_ufo;
- struct {
- VirtQueueElement elem;
- ssize_t len;
- } async_tx;
int mergeable_rx_bufs;
uint8_t promisc;
uint8_t allmulti;
} mac_table;
uint32_t *vlans;
DeviceState *qdev;
+ int multiqueue;
+ uint16_t max_queues;
+ uint16_t curr_queues;
+ size_t config_size;
} VirtIONet;
+/*
+ * Calculate the number of bytes up to and including the given 'field' of
+ * 'container'.
+ */
+#define endof(container, field) \
+ (offsetof(container, field) + sizeof(((container *)0)->field))
+
+typedef struct VirtIOFeature {
+ uint32_t flags;
+ size_t end;
+} VirtIOFeature;
+
+static VirtIOFeature feature_sizes[] = {
+ {.flags = 1 << VIRTIO_NET_F_MAC,
+ .end = endof(struct virtio_net_config, mac)},
+ {.flags = 1 << VIRTIO_NET_F_STATUS,
+ .end = endof(struct virtio_net_config, status)},
+ {.flags = 1 << VIRTIO_NET_F_MQ,
+ .end = endof(struct virtio_net_config, max_virtqueue_pairs)},
+ {}
+};
+
+static VirtIONetQueue *virtio_net_get_subqueue(NetClientState *nc)
+{
+ VirtIONet *n = qemu_get_nic_opaque(nc);
+
+ return &n->vqs[nc->queue_index];
+}
+
+static int vq2q(int queue_index)
+{
+ return queue_index / 2;
+}
+
/* TODO
* - we could suppress RX interrupt if we were so inclined.
*/
struct virtio_net_config netcfg;
stw_p(&netcfg.status, n->status);
+ stw_p(&netcfg.max_virtqueue_pairs, n->max_queues);
memcpy(netcfg.mac, n->mac, ETH_ALEN);
- memcpy(config, &netcfg, sizeof(netcfg));
+ memcpy(config, &netcfg, n->config_size);
}
static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config)
{
VirtIONet *n = to_virtio_net(vdev);
- struct virtio_net_config netcfg;
+ struct virtio_net_config netcfg = {};
- memcpy(&netcfg, config, sizeof(netcfg));
+ memcpy(&netcfg, config, n->config_size);
- if (memcmp(netcfg.mac, n->mac, ETH_ALEN)) {
+ if (!(n->vdev.guest_features >> VIRTIO_NET_F_CTRL_MAC_ADDR & 1) &&
+ memcmp(netcfg.mac, n->mac, ETH_ALEN)) {
memcpy(n->mac, netcfg.mac, ETH_ALEN);
- qemu_format_nic_info_str(&n->nic->nc, n->mac);
+ qemu_format_nic_info_str(qemu_get_queue(n->nic), n->mac);
}
}
static void virtio_net_vhost_status(VirtIONet *n, uint8_t status)
{
- if (!n->nic->nc.peer) {
+ NetClientState *nc = qemu_get_queue(n->nic);
+ int queues = n->multiqueue ? n->max_queues : 1;
+
+ if (!nc->peer) {
return;
}
- if (n->nic->nc.peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
+ if (nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
return;
}
- if (!tap_get_vhost_net(n->nic->nc.peer)) {
+ if (!tap_get_vhost_net(nc->peer)) {
return;
}
+
if (!!n->vhost_started == virtio_net_started(n, status) &&
- !n->nic->nc.peer->link_down) {
+ !nc->peer->link_down) {
return;
}
if (!n->vhost_started) {
int r;
- if (!vhost_net_query(tap_get_vhost_net(n->nic->nc.peer), &n->vdev)) {
+ if (!vhost_net_query(tap_get_vhost_net(nc->peer), &n->vdev)) {
return;
}
- r = vhost_net_start(tap_get_vhost_net(n->nic->nc.peer), &n->vdev);
+ n->vhost_started = 1;
+ r = vhost_net_start(&n->vdev, n->nic->ncs, queues);
if (r < 0) {
error_report("unable to start vhost net: %d: "
"falling back on userspace virtio", -r);
- } else {
- n->vhost_started = 1;
+ n->vhost_started = 0;
}
} else {
- vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), &n->vdev);
+ vhost_net_stop(&n->vdev, n->nic->ncs, queues);
n->vhost_started = 0;
}
}
static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
{
VirtIONet *n = to_virtio_net(vdev);
+ VirtIONetQueue *q;
+ int i;
+ uint8_t queue_status;
virtio_net_vhost_status(n, status);
- if (!n->tx_waiting) {
- return;
- }
+ for (i = 0; i < n->max_queues; i++) {
+ q = &n->vqs[i];
- if (virtio_net_started(n, status) && !n->vhost_started) {
- if (n->tx_timer) {
- qemu_mod_timer(n->tx_timer,
- qemu_get_clock_ns(vm_clock) + n->tx_timeout);
+ if ((!n->multiqueue && i != 0) || i >= n->curr_queues) {
+ queue_status = 0;
} else {
- qemu_bh_schedule(n->tx_bh);
+ queue_status = status;
}
- } else {
- if (n->tx_timer) {
- qemu_del_timer(n->tx_timer);
+
+ if (!q->tx_waiting) {
+ continue;
+ }
+
+ if (virtio_net_started(n, queue_status) && !n->vhost_started) {
+ if (q->tx_timer) {
+ qemu_mod_timer(q->tx_timer,
+ qemu_get_clock_ns(vm_clock) + n->tx_timeout);
+ } else {
+ qemu_bh_schedule(q->tx_bh);
+ }
} else {
- qemu_bh_cancel(n->tx_bh);
+ if (q->tx_timer) {
+ qemu_del_timer(q->tx_timer);
+ } else {
+ qemu_bh_cancel(q->tx_bh);
+ }
}
}
}
static void virtio_net_set_link_status(NetClientState *nc)
{
- VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
+ VirtIONet *n = qemu_get_nic_opaque(nc);
uint16_t old_status = n->status;
if (nc->link_down)
n->nomulti = 0;
n->nouni = 0;
n->nobcast = 0;
+ /* multiqueue is disabled by default */
+ n->curr_queues = 1;
/* Flush any MAC and VLAN filter table state */
n->mac_table.in_use = 0;
n->mac_table.multi_overflow = 0;
n->mac_table.uni_overflow = 0;
memset(n->mac_table.macs, 0, MAC_TABLE_ENTRIES * ETH_ALEN);
+ memcpy(&n->mac[0], &n->nic->conf->macaddr, sizeof(n->mac));
memset(n->vlans, 0, MAX_VLAN >> 3);
}
-static int peer_has_vnet_hdr(VirtIONet *n)
+static void peer_test_vnet_hdr(VirtIONet *n)
{
- if (!n->nic->nc.peer)
- return 0;
+ NetClientState *nc = qemu_get_queue(n->nic);
+ if (!nc->peer) {
+ return;
+ }
- if (n->nic->nc.peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP)
- return 0;
+ if (nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
+ return;
+ }
- n->has_vnet_hdr = tap_has_vnet_hdr(n->nic->nc.peer);
+ n->has_vnet_hdr = tap_has_vnet_hdr(nc->peer);
+}
+static int peer_has_vnet_hdr(VirtIONet *n)
+{
return n->has_vnet_hdr;
}
if (!peer_has_vnet_hdr(n))
return 0;
- n->has_ufo = tap_has_ufo(n->nic->nc.peer);
+ n->has_ufo = tap_has_ufo(qemu_get_queue(n->nic)->peer);
return n->has_ufo;
}
+static void virtio_net_set_mrg_rx_bufs(VirtIONet *n, int mergeable_rx_bufs)
+{
+ int i;
+ NetClientState *nc;
+
+ n->mergeable_rx_bufs = mergeable_rx_bufs;
+
+ n->guest_hdr_len = n->mergeable_rx_bufs ?
+ sizeof(struct virtio_net_hdr_mrg_rxbuf) : sizeof(struct virtio_net_hdr);
+
+ for (i = 0; i < n->max_queues; i++) {
+ nc = qemu_get_subqueue(n->nic, i);
+
+ if (peer_has_vnet_hdr(n) &&
+ tap_has_vnet_hdr_len(nc->peer, n->guest_hdr_len)) {
+ tap_set_vnet_hdr_len(nc->peer, n->guest_hdr_len);
+ n->host_hdr_len = n->guest_hdr_len;
+ }
+ }
+}
+
+static int peer_attach(VirtIONet *n, int index)
+{
+ NetClientState *nc = qemu_get_subqueue(n->nic, index);
+
+ if (!nc->peer) {
+ return 0;
+ }
+
+ if (nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
+ return 0;
+ }
+
+ return tap_enable(nc->peer);
+}
+
+static int peer_detach(VirtIONet *n, int index)
+{
+ NetClientState *nc = qemu_get_subqueue(n->nic, index);
+
+ if (!nc->peer) {
+ return 0;
+ }
+
+ if (nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
+ return 0;
+ }
+
+ return tap_disable(nc->peer);
+}
+
+static void virtio_net_set_queues(VirtIONet *n)
+{
+ int i;
+
+ for (i = 0; i < n->max_queues; i++) {
+ if (i < n->curr_queues) {
+ assert(!peer_attach(n, i));
+ } else {
+ assert(!peer_detach(n, i));
+ }
+ }
+}
+
+static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue, int ctrl);
+
static uint32_t virtio_net_get_features(VirtIODevice *vdev, uint32_t features)
{
VirtIONet *n = to_virtio_net(vdev);
+ NetClientState *nc = qemu_get_queue(n->nic);
features |= (1 << VIRTIO_NET_F_MAC);
- if (peer_has_vnet_hdr(n)) {
- tap_using_vnet_hdr(n->nic->nc.peer, 1);
- n->host_hdr_len = sizeof(struct virtio_net_hdr);
- } else {
+ if (!peer_has_vnet_hdr(n)) {
features &= ~(0x1 << VIRTIO_NET_F_CSUM);
features &= ~(0x1 << VIRTIO_NET_F_HOST_TSO4);
features &= ~(0x1 << VIRTIO_NET_F_HOST_TSO6);
features &= ~(0x1 << VIRTIO_NET_F_HOST_UFO);
}
- if (!n->nic->nc.peer ||
- n->nic->nc.peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
+ if (!nc->peer || nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
return features;
}
- if (!tap_get_vhost_net(n->nic->nc.peer)) {
+ if (!tap_get_vhost_net(nc->peer)) {
return features;
}
- return vhost_net_get_features(tap_get_vhost_net(n->nic->nc.peer), features);
+ return vhost_net_get_features(tap_get_vhost_net(nc->peer), features);
}
static uint32_t virtio_net_bad_features(VirtIODevice *vdev)
static void virtio_net_set_features(VirtIODevice *vdev, uint32_t features)
{
VirtIONet *n = to_virtio_net(vdev);
+ int i;
- n->mergeable_rx_bufs = !!(features & (1 << VIRTIO_NET_F_MRG_RXBUF));
- n->guest_hdr_len = n->mergeable_rx_bufs ?
- sizeof(struct virtio_net_hdr_mrg_rxbuf) : sizeof(struct virtio_net_hdr);
+ virtio_net_set_multiqueue(n, !!(features & (1 << VIRTIO_NET_F_MQ)),
+ !!(features & (1 << VIRTIO_NET_F_CTRL_VQ)));
+
+ virtio_net_set_mrg_rx_bufs(n, !!(features & (1 << VIRTIO_NET_F_MRG_RXBUF)));
if (n->has_vnet_hdr) {
- tap_set_offload(n->nic->nc.peer,
+ tap_set_offload(qemu_get_subqueue(n->nic, 0)->peer,
(features >> VIRTIO_NET_F_GUEST_CSUM) & 1,
(features >> VIRTIO_NET_F_GUEST_TSO4) & 1,
(features >> VIRTIO_NET_F_GUEST_TSO6) & 1,
(features >> VIRTIO_NET_F_GUEST_ECN) & 1,
(features >> VIRTIO_NET_F_GUEST_UFO) & 1);
}
- if (!n->nic->nc.peer ||
- n->nic->nc.peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
- return;
- }
- if (!tap_get_vhost_net(n->nic->nc.peer)) {
- return;
+
+ for (i = 0; i < n->max_queues; i++) {
+ NetClientState *nc = qemu_get_subqueue(n->nic, i);
+
+ if (!nc->peer || nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
+ continue;
+ }
+ if (!tap_get_vhost_net(nc->peer)) {
+ continue;
+ }
+ vhost_net_ack_features(tap_get_vhost_net(nc->peer), features);
}
- vhost_net_ack_features(tap_get_vhost_net(n->nic->nc.peer), features);
}
static int virtio_net_handle_rx_mode(VirtIONet *n, uint8_t cmd,
- VirtQueueElement *elem)
+ struct iovec *iov, unsigned int iov_cnt)
{
uint8_t on;
+ size_t s;
- if (elem->out_num != 2 || elem->out_sg[1].iov_len != sizeof(on)) {
- error_report("virtio-net ctrl invalid rx mode command");
- exit(1);
+ s = iov_to_buf(iov, iov_cnt, 0, &on, sizeof(on));
+ if (s != sizeof(on)) {
+ return VIRTIO_NET_ERR;
}
- on = ldub_p(elem->out_sg[1].iov_base);
-
- if (cmd == VIRTIO_NET_CTRL_RX_MODE_PROMISC)
+ if (cmd == VIRTIO_NET_CTRL_RX_PROMISC) {
n->promisc = on;
- else if (cmd == VIRTIO_NET_CTRL_RX_MODE_ALLMULTI)
+ } else if (cmd == VIRTIO_NET_CTRL_RX_ALLMULTI) {
n->allmulti = on;
- else if (cmd == VIRTIO_NET_CTRL_RX_MODE_ALLUNI)
+ } else if (cmd == VIRTIO_NET_CTRL_RX_ALLUNI) {
n->alluni = on;
- else if (cmd == VIRTIO_NET_CTRL_RX_MODE_NOMULTI)
+ } else if (cmd == VIRTIO_NET_CTRL_RX_NOMULTI) {
n->nomulti = on;
- else if (cmd == VIRTIO_NET_CTRL_RX_MODE_NOUNI)
+ } else if (cmd == VIRTIO_NET_CTRL_RX_NOUNI) {
n->nouni = on;
- else if (cmd == VIRTIO_NET_CTRL_RX_MODE_NOBCAST)
+ } else if (cmd == VIRTIO_NET_CTRL_RX_NOBCAST) {
n->nobcast = on;
- else
+ } else {
return VIRTIO_NET_ERR;
+ }
return VIRTIO_NET_OK;
}
static int virtio_net_handle_mac(VirtIONet *n, uint8_t cmd,
- VirtQueueElement *elem)
+ struct iovec *iov, unsigned int iov_cnt)
{
struct virtio_net_ctrl_mac mac_data;
+ size_t s;
- if (cmd != VIRTIO_NET_CTRL_MAC_TABLE_SET || elem->out_num != 3 ||
- elem->out_sg[1].iov_len < sizeof(mac_data) ||
- elem->out_sg[2].iov_len < sizeof(mac_data))
+ if (cmd == VIRTIO_NET_CTRL_MAC_ADDR_SET) {
+ if (iov_size(iov, iov_cnt) != sizeof(n->mac)) {
+ return VIRTIO_NET_ERR;
+ }
+ s = iov_to_buf(iov, iov_cnt, 0, &n->mac, sizeof(n->mac));
+ assert(s == sizeof(n->mac));
+ qemu_format_nic_info_str(qemu_get_queue(n->nic), n->mac);
+ return VIRTIO_NET_OK;
+ }
+
+ if (cmd != VIRTIO_NET_CTRL_MAC_TABLE_SET) {
return VIRTIO_NET_ERR;
+ }
n->mac_table.in_use = 0;
n->mac_table.first_multi = 0;
n->mac_table.multi_overflow = 0;
memset(n->mac_table.macs, 0, MAC_TABLE_ENTRIES * ETH_ALEN);
- mac_data.entries = ldl_p(elem->out_sg[1].iov_base);
+ s = iov_to_buf(iov, iov_cnt, 0, &mac_data.entries,
+ sizeof(mac_data.entries));
+ mac_data.entries = ldl_p(&mac_data.entries);
+ if (s != sizeof(mac_data.entries)) {
+ return VIRTIO_NET_ERR;
+ }
+ iov_discard_front(&iov, &iov_cnt, s);
- if (sizeof(mac_data.entries) +
- (mac_data.entries * ETH_ALEN) > elem->out_sg[1].iov_len)
+ if (mac_data.entries * ETH_ALEN > iov_size(iov, iov_cnt)) {
return VIRTIO_NET_ERR;
+ }
if (mac_data.entries <= MAC_TABLE_ENTRIES) {
- memcpy(n->mac_table.macs, elem->out_sg[1].iov_base + sizeof(mac_data),
- mac_data.entries * ETH_ALEN);
+ s = iov_to_buf(iov, iov_cnt, 0, n->mac_table.macs,
+ mac_data.entries * ETH_ALEN);
+ if (s != mac_data.entries * ETH_ALEN) {
+ return VIRTIO_NET_ERR;
+ }
n->mac_table.in_use += mac_data.entries;
} else {
n->mac_table.uni_overflow = 1;
}
+ iov_discard_front(&iov, &iov_cnt, mac_data.entries * ETH_ALEN);
+
n->mac_table.first_multi = n->mac_table.in_use;
- mac_data.entries = ldl_p(elem->out_sg[2].iov_base);
+ s = iov_to_buf(iov, iov_cnt, 0, &mac_data.entries,
+ sizeof(mac_data.entries));
+ mac_data.entries = ldl_p(&mac_data.entries);
+ if (s != sizeof(mac_data.entries)) {
+ return VIRTIO_NET_ERR;
+ }
- if (sizeof(mac_data.entries) +
- (mac_data.entries * ETH_ALEN) > elem->out_sg[2].iov_len)
+ iov_discard_front(&iov, &iov_cnt, s);
+
+ if (mac_data.entries * ETH_ALEN != iov_size(iov, iov_cnt)) {
return VIRTIO_NET_ERR;
+ }
- if (mac_data.entries) {
- if (n->mac_table.in_use + mac_data.entries <= MAC_TABLE_ENTRIES) {
- memcpy(n->mac_table.macs + (n->mac_table.in_use * ETH_ALEN),
- elem->out_sg[2].iov_base + sizeof(mac_data),
- mac_data.entries * ETH_ALEN);
- n->mac_table.in_use += mac_data.entries;
- } else {
- n->mac_table.multi_overflow = 1;
+ if (n->mac_table.in_use + mac_data.entries <= MAC_TABLE_ENTRIES) {
+ s = iov_to_buf(iov, iov_cnt, 0, n->mac_table.macs,
+ mac_data.entries * ETH_ALEN);
+ if (s != mac_data.entries * ETH_ALEN) {
+ return VIRTIO_NET_ERR;
}
+ n->mac_table.in_use += mac_data.entries;
+ } else {
+ n->mac_table.multi_overflow = 1;
}
return VIRTIO_NET_OK;
}
static int virtio_net_handle_vlan_table(VirtIONet *n, uint8_t cmd,
- VirtQueueElement *elem)
+ struct iovec *iov, unsigned int iov_cnt)
{
uint16_t vid;
+ size_t s;
- if (elem->out_num != 2 || elem->out_sg[1].iov_len != sizeof(vid)) {
- error_report("virtio-net ctrl invalid vlan command");
+ s = iov_to_buf(iov, iov_cnt, 0, &vid, sizeof(vid));
+ vid = lduw_p(&vid);
+ if (s != sizeof(vid)) {
return VIRTIO_NET_ERR;
}
- vid = lduw_p(elem->out_sg[1].iov_base);
-
if (vid >= MAX_VLAN)
return VIRTIO_NET_ERR;
return VIRTIO_NET_OK;
}
+static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd,
+ VirtQueueElement *elem)
+{
+ struct virtio_net_ctrl_mq s;
+
+ if (elem->out_num != 2 ||
+ elem->out_sg[1].iov_len != sizeof(struct virtio_net_ctrl_mq)) {
+ error_report("virtio-net ctrl invalid steering command");
+ return VIRTIO_NET_ERR;
+ }
+
+ if (cmd != VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET) {
+ return VIRTIO_NET_ERR;
+ }
+
+ memcpy(&s, elem->out_sg[1].iov_base, sizeof(struct virtio_net_ctrl_mq));
+
+ if (s.virtqueue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN ||
+ s.virtqueue_pairs > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX ||
+ s.virtqueue_pairs > n->max_queues ||
+ !n->multiqueue) {
+ return VIRTIO_NET_ERR;
+ }
+
+ n->curr_queues = s.virtqueue_pairs;
+ /* stop the backend before changing the number of queues to avoid handling a
+ * disabled queue */
+ virtio_net_set_status(&n->vdev, n->vdev.status);
+ virtio_net_set_queues(n);
+
+ return VIRTIO_NET_OK;
+}
static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIONet *n = to_virtio_net(vdev);
struct virtio_net_ctrl_hdr ctrl;
virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
VirtQueueElement elem;
+ size_t s;
+ struct iovec *iov;
+ unsigned int iov_cnt;
while (virtqueue_pop(vq, &elem)) {
- if ((elem.in_num < 1) || (elem.out_num < 1)) {
+ if (iov_size(elem.in_sg, elem.in_num) < sizeof(status) ||
+ iov_size(elem.out_sg, elem.out_num) < sizeof(ctrl)) {
error_report("virtio-net ctrl missing headers");
exit(1);
}
- if (elem.out_sg[0].iov_len < sizeof(ctrl) ||
- elem.in_sg[elem.in_num - 1].iov_len < sizeof(status)) {
- error_report("virtio-net ctrl header not in correct element");
- exit(1);
+ iov = elem.out_sg;
+ iov_cnt = elem.out_num;
+ s = iov_to_buf(iov, iov_cnt, 0, &ctrl, sizeof(ctrl));
+ iov_discard_front(&iov, &iov_cnt, sizeof(ctrl));
+ if (s != sizeof(ctrl)) {
+ status = VIRTIO_NET_ERR;
+ } else if (ctrl.class == VIRTIO_NET_CTRL_RX) {
+ status = virtio_net_handle_rx_mode(n, ctrl.cmd, iov, iov_cnt);
+ } else if (ctrl.class == VIRTIO_NET_CTRL_MAC) {
+ status = virtio_net_handle_mac(n, ctrl.cmd, iov, iov_cnt);
+ } else if (ctrl.class == VIRTIO_NET_CTRL_VLAN) {
+ status = virtio_net_handle_vlan_table(n, ctrl.cmd, iov, iov_cnt);
+ } else if (ctrl.class == VIRTIO_NET_CTRL_MQ) {
+ status = virtio_net_handle_mq(n, ctrl.cmd, &elem);
}
- ctrl.class = ldub_p(elem.out_sg[0].iov_base);
- ctrl.cmd = ldub_p(elem.out_sg[0].iov_base + sizeof(ctrl.class));
-
- if (ctrl.class == VIRTIO_NET_CTRL_RX_MODE)
- status = virtio_net_handle_rx_mode(n, ctrl.cmd, &elem);
- else if (ctrl.class == VIRTIO_NET_CTRL_MAC)
- status = virtio_net_handle_mac(n, ctrl.cmd, &elem);
- else if (ctrl.class == VIRTIO_NET_CTRL_VLAN)
- status = virtio_net_handle_vlan_table(n, ctrl.cmd, &elem);
-
- stb_p(elem.in_sg[elem.in_num - 1].iov_base, status);
+ s = iov_from_buf(elem.in_sg, elem.in_num, 0, &status, sizeof(status));
+ assert(s == sizeof(status));
virtqueue_push(vq, &elem, sizeof(status));
virtio_notify(vdev, vq);
static void virtio_net_handle_rx(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIONet *n = to_virtio_net(vdev);
+ int queue_index = vq2q(virtio_get_queue_index(vq));
- qemu_flush_queued_packets(&n->nic->nc);
+ qemu_flush_queued_packets(qemu_get_subqueue(n->nic, queue_index));
}
static int virtio_net_can_receive(NetClientState *nc)
{
- VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
+ VirtIONet *n = qemu_get_nic_opaque(nc);
+ VirtIONetQueue *q = virtio_net_get_subqueue(nc);
+
if (!n->vdev.vm_running) {
return 0;
}
- if (!virtio_queue_ready(n->rx_vq) ||
- !(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK))
+ if (nc->queue_index >= n->curr_queues) {
return 0;
+ }
+
+ if (!virtio_queue_ready(q->rx_vq) ||
+ !(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK)) {
+ return 0;
+ }
return 1;
}
-static int virtio_net_has_buffers(VirtIONet *n, int bufsize)
+static int virtio_net_has_buffers(VirtIONetQueue *q, int bufsize)
{
- if (virtio_queue_empty(n->rx_vq) ||
+ VirtIONet *n = q->n;
+ if (virtio_queue_empty(q->rx_vq) ||
(n->mergeable_rx_bufs &&
- !virtqueue_avail_bytes(n->rx_vq, bufsize, 0))) {
- virtio_queue_set_notification(n->rx_vq, 1);
+ !virtqueue_avail_bytes(q->rx_vq, bufsize, 0))) {
+ virtio_queue_set_notification(q->rx_vq, 1);
/* To avoid a race condition where the guest has made some buffers
* available after the above check but before notification was
* enabled, check for available buffers again.
*/
- if (virtio_queue_empty(n->rx_vq) ||
+ if (virtio_queue_empty(q->rx_vq) ||
(n->mergeable_rx_bufs &&
- !virtqueue_avail_bytes(n->rx_vq, bufsize, 0)))
+ !virtqueue_avail_bytes(q->rx_vq, bufsize, 0))) {
return 0;
+ }
}
- virtio_queue_set_notification(n->rx_vq, 0);
+ virtio_queue_set_notification(q->rx_vq, 0);
return 1;
}
static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, size_t size)
{
- VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
+ VirtIONet *n = qemu_get_nic_opaque(nc);
+ VirtIONetQueue *q = virtio_net_get_subqueue(nc);
struct iovec mhdr_sg[VIRTQUEUE_MAX_SIZE];
struct virtio_net_hdr_mrg_rxbuf mhdr;
unsigned mhdr_cnt = 0;
size_t offset, i, guest_offset;
- if (!virtio_net_can_receive(&n->nic->nc))
+ if (!virtio_net_can_receive(nc)) {
return -1;
+ }
/* hdr_len refers to the header we supply to the guest */
- if (!virtio_net_has_buffers(n, size + n->guest_hdr_len - n->host_hdr_len))
+ if (!virtio_net_has_buffers(q, size + n->guest_hdr_len - n->host_hdr_len)) {
return 0;
+ }
if (!receive_filter(n, buf, size))
return size;
total = 0;
- if (virtqueue_pop(n->rx_vq, &elem) == 0) {
+ if (virtqueue_pop(q->rx_vq, &elem) == 0) {
if (i == 0)
return -1;
error_report("virtio-net unexpected empty queue: "
}
/* signal other side */
- virtqueue_fill(n->rx_vq, &elem, total, i++);
+ virtqueue_fill(q->rx_vq, &elem, total, i++);
}
if (mhdr_cnt) {
&mhdr.num_buffers, sizeof mhdr.num_buffers);
}
- virtqueue_flush(n->rx_vq, i);
- virtio_notify(&n->vdev, n->rx_vq);
+ virtqueue_flush(q->rx_vq, i);
+ virtio_notify(&n->vdev, q->rx_vq);
return size;
}
-static int32_t virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq);
+static int32_t virtio_net_flush_tx(VirtIONetQueue *q);
static void virtio_net_tx_complete(NetClientState *nc, ssize_t len)
{
- VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
+ VirtIONet *n = qemu_get_nic_opaque(nc);
+ VirtIONetQueue *q = virtio_net_get_subqueue(nc);
- virtqueue_push(n->tx_vq, &n->async_tx.elem, 0);
- virtio_notify(&n->vdev, n->tx_vq);
+ virtqueue_push(q->tx_vq, &q->async_tx.elem, 0);
+ virtio_notify(&n->vdev, q->tx_vq);
- n->async_tx.elem.out_num = n->async_tx.len = 0;
+ q->async_tx.elem.out_num = q->async_tx.len = 0;
- virtio_queue_set_notification(n->tx_vq, 1);
- virtio_net_flush_tx(n, n->tx_vq);
+ virtio_queue_set_notification(q->tx_vq, 1);
+ virtio_net_flush_tx(q);
}
/* TX */
-static int32_t virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq)
+static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
{
+ VirtIONet *n = q->n;
VirtQueueElement elem;
int32_t num_packets = 0;
+ int queue_index = vq2q(virtio_get_queue_index(q->tx_vq));
if (!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK)) {
return num_packets;
}
assert(n->vdev.vm_running);
- if (n->async_tx.elem.out_num) {
- virtio_queue_set_notification(n->tx_vq, 0);
+ if (q->async_tx.elem.out_num) {
+ virtio_queue_set_notification(q->tx_vq, 0);
return num_packets;
}
- while (virtqueue_pop(vq, &elem)) {
+ while (virtqueue_pop(q->tx_vq, &elem)) {
ssize_t ret, len;
unsigned int out_num = elem.out_num;
struct iovec *out_sg = &elem.out_sg[0];
len = n->guest_hdr_len;
- ret = qemu_sendv_packet_async(&n->nic->nc, out_sg, out_num,
- virtio_net_tx_complete);
+ ret = qemu_sendv_packet_async(qemu_get_subqueue(n->nic, queue_index),
+ out_sg, out_num, virtio_net_tx_complete);
if (ret == 0) {
- virtio_queue_set_notification(n->tx_vq, 0);
- n->async_tx.elem = elem;
- n->async_tx.len = len;
+ virtio_queue_set_notification(q->tx_vq, 0);
+ q->async_tx.elem = elem;
+ q->async_tx.len = len;
return -EBUSY;
}
len += ret;
- virtqueue_push(vq, &elem, 0);
- virtio_notify(&n->vdev, vq);
+ virtqueue_push(q->tx_vq, &elem, 0);
+ virtio_notify(&n->vdev, q->tx_vq);
if (++num_packets >= n->tx_burst) {
break;
static void virtio_net_handle_tx_timer(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIONet *n = to_virtio_net(vdev);
+ VirtIONetQueue *q = &n->vqs[vq2q(virtio_get_queue_index(vq))];
/* This happens when device was stopped but VCPU wasn't. */
if (!n->vdev.vm_running) {
- n->tx_waiting = 1;
+ q->tx_waiting = 1;
return;
}
- if (n->tx_waiting) {
+ if (q->tx_waiting) {
virtio_queue_set_notification(vq, 1);
- qemu_del_timer(n->tx_timer);
- n->tx_waiting = 0;
- virtio_net_flush_tx(n, vq);
+ qemu_del_timer(q->tx_timer);
+ q->tx_waiting = 0;
+ virtio_net_flush_tx(q);
} else {
- qemu_mod_timer(n->tx_timer,
+ qemu_mod_timer(q->tx_timer,
qemu_get_clock_ns(vm_clock) + n->tx_timeout);
- n->tx_waiting = 1;
+ q->tx_waiting = 1;
virtio_queue_set_notification(vq, 0);
}
}
static void virtio_net_handle_tx_bh(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIONet *n = to_virtio_net(vdev);
+ VirtIONetQueue *q = &n->vqs[vq2q(virtio_get_queue_index(vq))];
- if (unlikely(n->tx_waiting)) {
+ if (unlikely(q->tx_waiting)) {
return;
}
- n->tx_waiting = 1;
+ q->tx_waiting = 1;
/* This happens when device was stopped but VCPU wasn't. */
if (!n->vdev.vm_running) {
return;
}
virtio_queue_set_notification(vq, 0);
- qemu_bh_schedule(n->tx_bh);
+ qemu_bh_schedule(q->tx_bh);
}
static void virtio_net_tx_timer(void *opaque)
{
- VirtIONet *n = opaque;
+ VirtIONetQueue *q = opaque;
+ VirtIONet *n = q->n;
assert(n->vdev.vm_running);
- n->tx_waiting = 0;
+ q->tx_waiting = 0;
/* Just in case the driver is not ready on more */
if (!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK))
return;
- virtio_queue_set_notification(n->tx_vq, 1);
- virtio_net_flush_tx(n, n->tx_vq);
+ virtio_queue_set_notification(q->tx_vq, 1);
+ virtio_net_flush_tx(q);
}
static void virtio_net_tx_bh(void *opaque)
{
- VirtIONet *n = opaque;
+ VirtIONetQueue *q = opaque;
+ VirtIONet *n = q->n;
int32_t ret;
assert(n->vdev.vm_running);
- n->tx_waiting = 0;
+ q->tx_waiting = 0;
/* Just in case the driver is not ready on more */
if (unlikely(!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK)))
return;
- ret = virtio_net_flush_tx(n, n->tx_vq);
+ ret = virtio_net_flush_tx(q);
if (ret == -EBUSY) {
return; /* Notification re-enable handled by tx_complete */
}
/* If we flush a full burst of packets, assume there are
* more coming and immediately reschedule */
if (ret >= n->tx_burst) {
- qemu_bh_schedule(n->tx_bh);
- n->tx_waiting = 1;
+ qemu_bh_schedule(q->tx_bh);
+ q->tx_waiting = 1;
return;
}
/* If less than a full burst, re-enable notification and flush
* anything that may have come in while we weren't looking. If
* we find something, assume the guest is still active and reschedule */
- virtio_queue_set_notification(n->tx_vq, 1);
- if (virtio_net_flush_tx(n, n->tx_vq) > 0) {
- virtio_queue_set_notification(n->tx_vq, 0);
- qemu_bh_schedule(n->tx_bh);
- n->tx_waiting = 1;
+ virtio_queue_set_notification(q->tx_vq, 1);
+ if (virtio_net_flush_tx(q) > 0) {
+ virtio_queue_set_notification(q->tx_vq, 0);
+ qemu_bh_schedule(q->tx_bh);
+ q->tx_waiting = 1;
}
}
+static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue, int ctrl)
+{
+ VirtIODevice *vdev = &n->vdev;
+ int i, max = multiqueue ? n->max_queues : 1;
+
+ n->multiqueue = multiqueue;
+
+ for (i = 2; i <= n->max_queues * 2 + 1; i++) {
+ virtio_del_queue(vdev, i);
+ }
+
+ for (i = 1; i < max; i++) {
+ n->vqs[i].rx_vq = virtio_add_queue(vdev, 256, virtio_net_handle_rx);
+ if (n->vqs[i].tx_timer) {
+ n->vqs[i].tx_vq =
+ virtio_add_queue(vdev, 256, virtio_net_handle_tx_timer);
+ n->vqs[i].tx_timer = qemu_new_timer_ns(vm_clock,
+ virtio_net_tx_timer,
+ &n->vqs[i]);
+ } else {
+ n->vqs[i].tx_vq =
+ virtio_add_queue(vdev, 256, virtio_net_handle_tx_bh);
+ n->vqs[i].tx_bh = qemu_bh_new(virtio_net_tx_bh, &n->vqs[i]);
+ }
+
+ n->vqs[i].tx_waiting = 0;
+ n->vqs[i].n = n;
+ }
+
+ if (ctrl) {
+ n->ctrl_vq = virtio_add_queue(vdev, 64, virtio_net_handle_ctrl);
+ }
+
+ virtio_net_set_queues(n);
+}
+
static void virtio_net_save(QEMUFile *f, void *opaque)
{
+ int i;
VirtIONet *n = opaque;
/* At this point, backend must be stopped, otherwise
virtio_save(&n->vdev, f);
qemu_put_buffer(f, n->mac, ETH_ALEN);
- qemu_put_be32(f, n->tx_waiting);
+ 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->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);
+ }
+ }
}
static int virtio_net_load(QEMUFile *f, void *opaque, int version_id)
{
VirtIONet *n = opaque;
- int i;
- int ret;
+ int ret, i, link_down;
if (version_id < 2 || version_id > VIRTIO_NET_VM_VERSION)
return -EINVAL;
}
qemu_get_buffer(f, n->mac, ETH_ALEN);
- n->tx_waiting = qemu_get_be32(f);
- n->mergeable_rx_bufs = qemu_get_be32(f);
- n->guest_hdr_len = n->mergeable_rx_bufs ?
- sizeof(struct virtio_net_hdr_mrg_rxbuf) : sizeof(struct virtio_net_hdr);
+ n->vqs[0].tx_waiting = qemu_get_be32(f);
+
+ virtio_net_set_mrg_rx_bufs(n, qemu_get_be32(f));
if (version_id >= 3)
n->status = qemu_get_be16(f);
}
if (n->has_vnet_hdr) {
- tap_using_vnet_hdr(n->nic->nc.peer, 1);
- n->host_hdr_len = sizeof(struct virtio_net_hdr);
- tap_set_offload(n->nic->nc.peer,
+ tap_set_offload(qemu_get_queue(n->nic)->peer,
(n->vdev.guest_features >> VIRTIO_NET_F_GUEST_CSUM) & 1,
(n->vdev.guest_features >> VIRTIO_NET_F_GUEST_TSO4) & 1,
(n->vdev.guest_features >> VIRTIO_NET_F_GUEST_TSO6) & 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);
+ for (i = 1; i < n->curr_queues; i++) {
+ n->vqs[i].tx_waiting = qemu_get_be32(f);
+ }
+ }
+
+ virtio_net_set_queues(n);
+
/* Find the first multicast entry in the saved MAC filter */
for (i = 0; i < n->mac_table.in_use; i++) {
if (n->mac_table.macs[i * ETH_ALEN] & 1) {
/* nc.link_down can't be migrated, so infer link_down according
* to link status bit in n->status */
- n->nic->nc.link_down = (n->status & VIRTIO_NET_S_LINK_UP) == 0;
+ link_down = (n->status & VIRTIO_NET_S_LINK_UP) == 0;
+ for (i = 0; i < n->max_queues; i++) {
+ qemu_get_subqueue(n->nic, i)->link_down = link_down;
+ }
return 0;
}
static void virtio_net_cleanup(NetClientState *nc)
{
- VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
+ VirtIONet *n = qemu_get_nic_opaque(nc);
n->nic = NULL;
}
.link_status_changed = virtio_net_set_link_status,
};
+static bool virtio_net_guest_notifier_pending(VirtIODevice *vdev, int idx)
+{
+ VirtIONet *n = to_virtio_net(vdev);
+ NetClientState *nc = qemu_get_subqueue(n->nic, vq2q(idx));
+ assert(n->vhost_started);
+ return vhost_net_virtqueue_pending(tap_get_vhost_net(nc->peer), idx);
+}
+
+static void virtio_net_guest_notifier_mask(VirtIODevice *vdev, int idx,
+ bool mask)
+{
+ VirtIONet *n = to_virtio_net(vdev);
+ NetClientState *nc = qemu_get_subqueue(n->nic, vq2q(idx));
+ assert(n->vhost_started);
+ vhost_net_virtqueue_mask(tap_get_vhost_net(nc->peer),
+ vdev, idx, mask);
+}
+
VirtIODevice *virtio_net_init(DeviceState *dev, NICConf *conf,
- virtio_net_conf *net)
+ virtio_net_conf *net, uint32_t host_features)
{
VirtIONet *n;
+ int i, config_size = 0;
+
+ for (i = 0; feature_sizes[i].flags != 0; i++) {
+ if (host_features & feature_sizes[i].flags) {
+ config_size = MAX(feature_sizes[i].end, config_size);
+ }
+ }
n = (VirtIONet *)virtio_common_init("virtio-net", VIRTIO_ID_NET,
- sizeof(struct virtio_net_config),
- sizeof(VirtIONet));
+ config_size, sizeof(VirtIONet));
+ n->config_size = config_size;
n->vdev.get_config = virtio_net_get_config;
n->vdev.set_config = virtio_net_set_config;
n->vdev.get_features = virtio_net_get_features;
n->vdev.bad_features = virtio_net_bad_features;
n->vdev.reset = virtio_net_reset;
n->vdev.set_status = virtio_net_set_status;
- n->rx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_rx);
+ n->vdev.guest_notifier_mask = virtio_net_guest_notifier_mask;
+ n->vdev.guest_notifier_pending = virtio_net_guest_notifier_pending;
+ n->vqs[0].rx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_rx);
+ n->max_queues = conf->queues;
+ n->curr_queues = 1;
+ n->vqs[0].n = n;
+ n->tx_timeout = net->txtimer;
if (net->tx && strcmp(net->tx, "timer") && strcmp(net->tx, "bh")) {
error_report("virtio-net: "
}
if (net->tx && !strcmp(net->tx, "timer")) {
- n->tx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_tx_timer);
- n->tx_timer = qemu_new_timer_ns(vm_clock, virtio_net_tx_timer, n);
- n->tx_timeout = net->txtimer;
+ n->vqs[0].tx_vq = virtio_add_queue(&n->vdev, 256,
+ virtio_net_handle_tx_timer);
+ n->vqs[0].tx_timer = qemu_new_timer_ns(vm_clock, virtio_net_tx_timer,
+ &n->vqs[0]);
} else {
- n->tx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_tx_bh);
- n->tx_bh = qemu_bh_new(virtio_net_tx_bh, n);
+ n->vqs[0].tx_vq = virtio_add_queue(&n->vdev, 256,
+ virtio_net_handle_tx_bh);
+ n->vqs[0].tx_bh = qemu_bh_new(virtio_net_tx_bh, &n->vqs[0]);
}
n->ctrl_vq = virtio_add_queue(&n->vdev, 64, virtio_net_handle_ctrl);
qemu_macaddr_default_if_unset(&conf->macaddr);
n->status = VIRTIO_NET_S_LINK_UP;
n->nic = qemu_new_nic(&net_virtio_info, conf, object_get_typename(OBJECT(dev)), dev->id, n);
+ peer_test_vnet_hdr(n);
+ if (peer_has_vnet_hdr(n)) {
+ for (i = 0; i < n->max_queues; i++) {
+ tap_using_vnet_hdr(qemu_get_subqueue(n->nic, i)->peer, true);
+ }
+ n->host_hdr_len = sizeof(struct virtio_net_hdr);
+ } else {
+ n->host_hdr_len = 0;
+ }
- qemu_format_nic_info_str(&n->nic->nc, conf->macaddr.a);
+ qemu_format_nic_info_str(qemu_get_queue(n->nic), conf->macaddr.a);
- n->tx_waiting = 0;
+ n->vqs[0].tx_waiting = 0;
n->tx_burst = net->txburst;
- n->mergeable_rx_bufs = 0;
- n->guest_hdr_len = sizeof(struct virtio_net_hdr);
+ virtio_net_set_mrg_rx_bufs(n, 0);
n->promisc = 1; /* for compatibility */
n->mac_table.macs = g_malloc0(MAC_TABLE_ENTRIES * ETH_ALEN);
void virtio_net_exit(VirtIODevice *vdev)
{
VirtIONet *n = DO_UPCAST(VirtIONet, vdev, vdev);
+ int i;
/* This will stop vhost backend if appropriate. */
virtio_net_set_status(vdev, 0);
- qemu_purge_queued_packets(&n->nic->nc);
-
unregister_savevm(n->qdev, "virtio-net", n);
g_free(n->mac_table.macs);
g_free(n->vlans);
- if (n->tx_timer) {
- qemu_del_timer(n->tx_timer);
- qemu_free_timer(n->tx_timer);
- } else {
- qemu_bh_delete(n->tx_bh);
+ for (i = 0; i < n->max_queues; i++) {
+ VirtIONetQueue *q = &n->vqs[i];
+ NetClientState *nc = qemu_get_subqueue(n->nic, i);
+
+ qemu_purge_queued_packets(nc);
+
+ if (q->tx_timer) {
+ qemu_del_timer(q->tx_timer);
+ qemu_free_timer(q->tx_timer);
+ } else {
+ qemu_bh_delete(q->tx_bh);
+ }
}
- qemu_del_net_client(&n->nic->nc);
+ qemu_del_nic(n->nic);
virtio_cleanup(&n->vdev);
}
projects / qemu.git / blobdiff