*
*/
+#include "iov.h"
#include "virtio.h"
#include "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"
-#define VIRTIO_NET_VM_VERSION 10
+#define VIRTIO_NET_VM_VERSION 11
#define MAC_TABLE_ENTRIES 64
#define MAX_VLAN (1 << 12) /* Per 802.1Q definition */
VirtQueue *rx_vq;
VirtQueue *tx_vq;
VirtQueue *ctrl_vq;
- VLANClientState *vc;
+ NICState *nic;
QEMUTimer *tx_timer;
- int tx_timer_active;
+ QEMUBH *tx_bh;
+ uint32_t tx_timeout;
+ int32_t tx_burst;
+ int tx_waiting;
+ uint32_t has_vnet_hdr;
+ uint8_t has_ufo;
struct {
VirtQueueElement elem;
ssize_t len;
uint8_t nomulti;
uint8_t nouni;
uint8_t nobcast;
+ uint8_t vhost_started;
struct {
int in_use;
int first_multi;
uint8_t *macs;
} mac_table;
uint32_t *vlans;
+ DeviceState *qdev;
} VirtIONet;
/* TODO
VirtIONet *n = to_virtio_net(vdev);
struct virtio_net_config netcfg;
- netcfg.status = n->status;
+ stw_p(&netcfg.status, n->status);
memcpy(netcfg.mac, n->mac, ETH_ALEN);
memcpy(config, &netcfg, sizeof(netcfg));
}
if (memcmp(netcfg.mac, n->mac, ETH_ALEN)) {
memcpy(n->mac, netcfg.mac, ETH_ALEN);
- qemu_format_nic_info_str(n->vc, n->mac);
+ qemu_format_nic_info_str(&n->nic->nc, n->mac);
}
}
-static void virtio_net_set_link_status(VLANClientState *vc)
+static bool virtio_net_started(VirtIONet *n, uint8_t status)
{
- VirtIONet *n = vc->opaque;
+ return (status & VIRTIO_CONFIG_S_DRIVER_OK) &&
+ (n->status & VIRTIO_NET_S_LINK_UP) && n->vdev.vm_running;
+}
+
+static void virtio_net_vhost_status(VirtIONet *n, uint8_t status)
+{
+ if (!n->nic->nc.peer) {
+ return;
+ }
+ if (n->nic->nc.peer->info->type != NET_CLIENT_TYPE_TAP) {
+ return;
+ }
+
+ if (!tap_get_vhost_net(n->nic->nc.peer)) {
+ return;
+ }
+ if (!!n->vhost_started == virtio_net_started(n, status) &&
+ !n->nic->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)) {
+ return;
+ }
+ r = vhost_net_start(tap_get_vhost_net(n->nic->nc.peer), &n->vdev);
+ if (r < 0) {
+ error_report("unable to start vhost net: %d: "
+ "falling back on userspace virtio", -r);
+ } else {
+ n->vhost_started = 1;
+ }
+ } else {
+ vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), &n->vdev);
+ n->vhost_started = 0;
+ }
+}
+
+static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
+{
+ VirtIONet *n = to_virtio_net(vdev);
+
+ virtio_net_vhost_status(n, status);
+
+ if (!n->tx_waiting) {
+ return;
+ }
+
+ 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);
+ } else {
+ qemu_bh_schedule(n->tx_bh);
+ }
+ } else {
+ if (n->tx_timer) {
+ qemu_del_timer(n->tx_timer);
+ } else {
+ qemu_bh_cancel(n->tx_bh);
+ }
+ }
+}
+
+static void virtio_net_set_link_status(VLANClientState *nc)
+{
+ VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
uint16_t old_status = n->status;
- if (vc->link_down)
+ if (nc->link_down)
n->status &= ~VIRTIO_NET_S_LINK_UP;
else
n->status |= VIRTIO_NET_S_LINK_UP;
if (n->status != old_status)
virtio_notify_config(&n->vdev);
+
+ virtio_net_set_status(&n->vdev, n->vdev.status);
}
static void virtio_net_reset(VirtIODevice *vdev)
memset(n->vlans, 0, MAX_VLAN >> 3);
}
-static uint32_t virtio_net_get_features(VirtIODevice *vdev)
+static int peer_has_vnet_hdr(VirtIONet *n)
{
- uint32_t features = (1 << VIRTIO_NET_F_MAC) |
- (1 << VIRTIO_NET_F_MRG_RXBUF) |
- (1 << VIRTIO_NET_F_STATUS) |
- (1 << VIRTIO_NET_F_CTRL_VQ) |
- (1 << VIRTIO_NET_F_CTRL_RX) |
- (1 << VIRTIO_NET_F_CTRL_VLAN) |
- (1 << VIRTIO_NET_F_CTRL_RX_EXTRA);
+ if (!n->nic->nc.peer)
+ return 0;
- return features;
+ if (n->nic->nc.peer->info->type != NET_CLIENT_TYPE_TAP)
+ return 0;
+
+ n->has_vnet_hdr = tap_has_vnet_hdr(n->nic->nc.peer);
+
+ return n->has_vnet_hdr;
+}
+
+static int peer_has_ufo(VirtIONet *n)
+{
+ if (!peer_has_vnet_hdr(n))
+ return 0;
+
+ n->has_ufo = tap_has_ufo(n->nic->nc.peer);
+
+ return n->has_ufo;
+}
+
+static uint32_t virtio_net_get_features(VirtIODevice *vdev, uint32_t features)
+{
+ VirtIONet *n = to_virtio_net(vdev);
+
+ features |= (1 << VIRTIO_NET_F_MAC);
+
+ if (peer_has_vnet_hdr(n)) {
+ tap_using_vnet_hdr(n->nic->nc.peer, 1);
+ } else {
+ 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_ECN);
+
+ features &= ~(0x1 << VIRTIO_NET_F_GUEST_CSUM);
+ features &= ~(0x1 << VIRTIO_NET_F_GUEST_TSO4);
+ features &= ~(0x1 << VIRTIO_NET_F_GUEST_TSO6);
+ features &= ~(0x1 << VIRTIO_NET_F_GUEST_ECN);
+ }
+
+ if (!peer_has_vnet_hdr(n) || !peer_has_ufo(n)) {
+ features &= ~(0x1 << VIRTIO_NET_F_GUEST_UFO);
+ features &= ~(0x1 << VIRTIO_NET_F_HOST_UFO);
+ }
+
+ if (!n->nic->nc.peer ||
+ n->nic->nc.peer->info->type != NET_CLIENT_TYPE_TAP) {
+ return features;
+ }
+ if (!tap_get_vhost_net(n->nic->nc.peer)) {
+ return features;
+ }
+ return vhost_net_get_features(tap_get_vhost_net(n->nic->nc.peer), features);
}
static uint32_t virtio_net_bad_features(VirtIODevice *vdev)
/* Linux kernel 2.6.25. It understood MAC (as everyone must),
* but also these: */
features |= (1 << VIRTIO_NET_F_MAC);
- features |= (1 << VIRTIO_NET_F_GUEST_CSUM);
- features |= (1 << VIRTIO_NET_F_GUEST_TSO4);
- features |= (1 << VIRTIO_NET_F_GUEST_TSO6);
- features |= (1 << VIRTIO_NET_F_GUEST_ECN);
+ features |= (1 << VIRTIO_NET_F_CSUM);
+ features |= (1 << VIRTIO_NET_F_HOST_TSO4);
+ features |= (1 << VIRTIO_NET_F_HOST_TSO6);
+ features |= (1 << VIRTIO_NET_F_HOST_ECN);
- return features & virtio_net_get_features(vdev);
+ return features;
}
static void virtio_net_set_features(VirtIODevice *vdev, uint32_t features)
VirtIONet *n = to_virtio_net(vdev);
n->mergeable_rx_bufs = !!(features & (1 << VIRTIO_NET_F_MRG_RXBUF));
+
+ if (n->has_vnet_hdr) {
+ tap_set_offload(n->nic->nc.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_TYPE_TAP) {
+ return;
+ }
+ if (!tap_get_vhost_net(n->nic->nc.peer)) {
+ return;
+ }
+ 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,
uint8_t on;
if (elem->out_num != 2 || elem->out_sg[1].iov_len != sizeof(on)) {
- fprintf(stderr, "virtio-net ctrl invalid rx mode command\n");
+ error_report("virtio-net ctrl invalid rx mode command");
exit(1);
}
n->mac_table.multi_overflow = 0;
memset(n->mac_table.macs, 0, MAC_TABLE_ENTRIES * ETH_ALEN);
- mac_data.entries = ldl_le_p(elem->out_sg[1].iov_base);
+ mac_data.entries = ldl_p(elem->out_sg[1].iov_base);
if (sizeof(mac_data.entries) +
(mac_data.entries * ETH_ALEN) > elem->out_sg[1].iov_len)
n->mac_table.first_multi = n->mac_table.in_use;
- mac_data.entries = ldl_le_p(elem->out_sg[2].iov_base);
+ mac_data.entries = ldl_p(elem->out_sg[2].iov_base);
if (sizeof(mac_data.entries) +
(mac_data.entries * ETH_ALEN) > elem->out_sg[2].iov_len)
uint16_t vid;
if (elem->out_num != 2 || elem->out_sg[1].iov_len != sizeof(vid)) {
- fprintf(stderr, "virtio-net ctrl invalid vlan command\n");
+ error_report("virtio-net ctrl invalid vlan command");
return VIRTIO_NET_ERR;
}
- vid = lduw_le_p(elem->out_sg[1].iov_base);
+ vid = lduw_p(elem->out_sg[1].iov_base);
if (vid >= MAX_VLAN)
return VIRTIO_NET_ERR;
while (virtqueue_pop(vq, &elem)) {
if ((elem.in_num < 1) || (elem.out_num < 1)) {
- fprintf(stderr, "virtio-net ctrl missing headers\n");
+ 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)) {
- fprintf(stderr, "virtio-net ctrl header not in correct element\n");
+ error_report("virtio-net ctrl header not in correct element");
exit(1);
}
{
VirtIONet *n = to_virtio_net(vdev);
- qemu_flush_queued_packets(n->vc);
+ qemu_flush_queued_packets(&n->nic->nc);
+
+ /* We now have RX buffers, signal to the IO thread to break out of the
+ * select to re-poll the tap file descriptor */
+ qemu_notify_event();
}
-static int do_virtio_net_can_receive(VirtIONet *n, int bufsize)
+static int virtio_net_can_receive(VLANClientState *nc)
{
+ VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
+ if (!n->vdev.vm_running) {
+ return 0;
+ }
+
if (!virtio_queue_ready(n->rx_vq) ||
!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK))
return 0;
+ return 1;
+}
+
+static int virtio_net_has_buffers(VirtIONet *n, int bufsize)
+{
if (virtio_queue_empty(n->rx_vq) ||
(n->mergeable_rx_bufs &&
!virtqueue_avail_bytes(n->rx_vq, bufsize, 0))) {
virtio_queue_set_notification(n->rx_vq, 1);
- return 0;
+
+ /* 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) ||
+ (n->mergeable_rx_bufs &&
+ !virtqueue_avail_bytes(n->rx_vq, bufsize, 0)))
+ return 0;
}
virtio_queue_set_notification(n->rx_vq, 0);
return 1;
}
-static int virtio_net_can_receive(VLANClientState *vc)
-{
- VirtIONet *n = vc->opaque;
-
- return do_virtio_net_can_receive(n, VIRTIO_NET_MAX_BUFSIZE);
-}
-
-static int iov_fill(struct iovec *iov, int iovcnt, const void *buf, int count)
+/* dhclient uses AF_PACKET but doesn't pass auxdata to the kernel so
+ * it never finds out that the packets don't have valid checksums. This
+ * causes dhclient to get upset. Fedora's carried a patch for ages to
+ * fix this with Xen but it hasn't appeared in an upstream release of
+ * dhclient yet.
+ *
+ * To avoid breaking existing guests, we catch udp packets and add
+ * checksums. This is terrible but it's better than hacking the guest
+ * kernels.
+ *
+ * N.B. if we introduce a zero-copy API, this operation is no longer free so
+ * we should provide a mechanism to disable it to avoid polluting the host
+ * cache.
+ */
+static void work_around_broken_dhclient(struct virtio_net_hdr *hdr,
+ const uint8_t *buf, size_t size)
{
- int offset, i;
-
- offset = i = 0;
- while (offset < count && i < iovcnt) {
- int len = MIN(iov[i].iov_len, count - offset);
- memcpy(iov[i].iov_base, buf + offset, len);
- offset += len;
- i++;
+ if ((hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && /* missing csum */
+ (size > 27 && size < 1500) && /* normal sized MTU */
+ (buf[12] == 0x08 && buf[13] == 0x00) && /* ethertype == IPv4 */
+ (buf[23] == 17) && /* ip.protocol == UDP */
+ (buf[34] == 0 && buf[35] == 67)) { /* udp.srcport == bootps */
+ /* FIXME this cast is evil */
+ net_checksum_calculate((uint8_t *)buf, size);
+ hdr->flags &= ~VIRTIO_NET_HDR_F_NEEDS_CSUM;
}
-
- return offset;
}
static int receive_header(VirtIONet *n, struct iovec *iov, int iovcnt,
hdr->flags = 0;
hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
+ if (n->has_vnet_hdr) {
+ memcpy(hdr, buf, sizeof(*hdr));
+ offset = sizeof(*hdr);
+ work_around_broken_dhclient(hdr, buf + offset, size - offset);
+ }
+
/* We only ever receive a struct virtio_net_hdr from the tapfd,
* but we may be passing along a larger header to the guest.
*/
if (n->promisc)
return 1;
+ if (n->has_vnet_hdr) {
+ ptr += sizeof(struct virtio_net_hdr);
+ }
+
if (!memcmp(&ptr[12], vlan, sizeof(vlan))) {
int vid = be16_to_cpup((uint16_t *)(ptr + 14)) & 0xfff;
if (!(n->vlans[vid >> 5] & (1U << (vid & 0x1f))))
return 0;
}
-static ssize_t virtio_net_receive(VLANClientState *vc, const uint8_t *buf, size_t size)
+static ssize_t virtio_net_receive(VLANClientState *nc, const uint8_t *buf, size_t size)
{
- VirtIONet *n = vc->opaque;
+ VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
struct virtio_net_hdr_mrg_rxbuf *mhdr = NULL;
- size_t hdr_len, offset, i;
+ size_t guest_hdr_len, offset, i, host_hdr_len;
+
+ if (!virtio_net_can_receive(&n->nic->nc))
+ return -1;
+
+ /* hdr_len refers to the header we supply to the guest */
+ guest_hdr_len = n->mergeable_rx_bufs ?
+ sizeof(struct virtio_net_hdr_mrg_rxbuf) : sizeof(struct virtio_net_hdr);
- if (!do_virtio_net_can_receive(n, size))
+
+ host_hdr_len = n->has_vnet_hdr ? sizeof(struct virtio_net_hdr) : 0;
+ if (!virtio_net_has_buffers(n, size + guest_hdr_len - host_hdr_len))
return 0;
if (!receive_filter(n, buf, size))
return size;
- /* hdr_len refers to the header we supply to the guest */
- hdr_len = n->mergeable_rx_bufs ?
- sizeof(struct virtio_net_hdr_mrg_rxbuf) : sizeof(struct virtio_net_hdr);
-
offset = i = 0;
while (offset < size) {
int len, total;
struct iovec sg[VIRTQUEUE_MAX_SIZE];
- len = total = 0;
+ total = 0;
- if ((i != 0 && !n->mergeable_rx_bufs) ||
- virtqueue_pop(n->rx_vq, &elem) == 0) {
+ if (virtqueue_pop(n->rx_vq, &elem) == 0) {
if (i == 0)
return -1;
- fprintf(stderr, "virtio-net truncating packet\n");
+ error_report("virtio-net unexpected empty queue: "
+ "i %zd mergeable %d offset %zd, size %zd, "
+ "guest hdr len %zd, host hdr len %zd guest features 0x%x",
+ i, n->mergeable_rx_bufs, offset, size,
+ guest_hdr_len, host_hdr_len, n->vdev.guest_features);
exit(1);
}
if (elem.in_num < 1) {
- fprintf(stderr, "virtio-net receive queue contains no in buffers\n");
+ error_report("virtio-net receive queue contains no in buffers");
exit(1);
}
- if (!n->mergeable_rx_bufs && elem.in_sg[0].iov_len != hdr_len) {
- fprintf(stderr, "virtio-net header not in first element\n");
+ if (!n->mergeable_rx_bufs && elem.in_sg[0].iov_len != guest_hdr_len) {
+ error_report("virtio-net header not in first element");
exit(1);
}
mhdr = (struct virtio_net_hdr_mrg_rxbuf *)sg[0].iov_base;
offset += receive_header(n, sg, elem.in_num,
- buf + offset, size - offset, hdr_len);
- total += hdr_len;
+ buf + offset, size - offset, guest_hdr_len);
+ total += guest_hdr_len;
}
/* copy in packet. ugh */
- len = iov_fill(sg, elem.in_num,
- buf + offset, size - offset);
+ len = iov_from_buf(sg, elem.in_num,
+ buf + offset, 0, size - offset);
total += len;
+ offset += len;
+ /* If buffers can't be merged, at this point we
+ * must have consumed the complete packet.
+ * Otherwise, drop it. */
+ if (!n->mergeable_rx_bufs && offset < size) {
+#if 0
+ error_report("virtio-net truncated non-mergeable packet: "
+ "i %zd mergeable %d offset %zd, size %zd, "
+ "guest hdr len %zd, host hdr len %zd",
+ i, n->mergeable_rx_bufs,
+ offset, size, guest_hdr_len, host_hdr_len);
+#endif
+ return size;
+ }
/* signal other side */
virtqueue_fill(n->rx_vq, &elem, total, i++);
-
- offset += len;
}
- if (mhdr)
- mhdr->num_buffers = i;
+ if (mhdr) {
+ stw_p(&mhdr->num_buffers, i);
+ }
virtqueue_flush(n->rx_vq, i);
virtio_notify(&n->vdev, n->rx_vq);
return size;
}
-static void virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq);
+static int32_t virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq);
-static void virtio_net_tx_complete(VLANClientState *vc, ssize_t len)
+static void virtio_net_tx_complete(VLANClientState *nc, ssize_t len)
{
- VirtIONet *n = vc->opaque;
+ VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
virtqueue_push(n->tx_vq, &n->async_tx.elem, n->async_tx.len);
virtio_notify(&n->vdev, n->tx_vq);
}
/* TX */
-static void virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq)
+static int32_t virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq)
{
VirtQueueElement elem;
- int has_vnet_hdr = 0;
+ int32_t num_packets = 0;
+ if (!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK)) {
+ return num_packets;
+ }
- if (!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK))
- return;
+ assert(n->vdev.vm_running);
if (n->async_tx.elem.out_num) {
virtio_queue_set_notification(n->tx_vq, 0);
- return;
+ return num_packets;
}
while (virtqueue_pop(vq, &elem)) {
sizeof(struct virtio_net_hdr);
if (out_num < 1 || out_sg->iov_len != hdr_len) {
- fprintf(stderr, "virtio-net header not in first element\n");
+ error_report("virtio-net header not in first element");
exit(1);
}
/* ignore the header if GSO is not supported */
- if (!has_vnet_hdr) {
+ if (!n->has_vnet_hdr) {
out_num--;
out_sg++;
len += hdr_len;
len += hdr_len;
}
- ret = qemu_sendv_packet_async(n->vc, out_sg, out_num,
+ ret = qemu_sendv_packet_async(&n->nic->nc, 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;
- return;
+ return -EBUSY;
}
len += ret;
virtqueue_push(vq, &elem, len);
virtio_notify(&n->vdev, vq);
+
+ if (++num_packets >= n->tx_burst) {
+ break;
+ }
}
+ return num_packets;
}
-static void virtio_net_handle_tx(VirtIODevice *vdev, VirtQueue *vq)
+static void virtio_net_handle_tx_timer(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIONet *n = to_virtio_net(vdev);
- if (n->tx_timer_active) {
+ /* This happens when device was stopped but VCPU wasn't. */
+ if (!n->vdev.vm_running) {
+ n->tx_waiting = 1;
+ return;
+ }
+
+ if (n->tx_waiting) {
virtio_queue_set_notification(vq, 1);
qemu_del_timer(n->tx_timer);
- n->tx_timer_active = 0;
+ n->tx_waiting = 0;
virtio_net_flush_tx(n, vq);
} else {
qemu_mod_timer(n->tx_timer,
- qemu_get_clock(vm_clock) + TX_TIMER_INTERVAL);
- n->tx_timer_active = 1;
+ qemu_get_clock_ns(vm_clock) + n->tx_timeout);
+ n->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);
+
+ if (unlikely(n->tx_waiting)) {
+ return;
+ }
+ n->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);
+}
+
static void virtio_net_tx_timer(void *opaque)
{
VirtIONet *n = opaque;
+ assert(n->vdev.vm_running);
- n->tx_timer_active = 0;
+ n->tx_waiting = 0;
/* Just in case the driver is not ready on more */
if (!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK))
virtio_net_flush_tx(n, n->tx_vq);
}
+static void virtio_net_tx_bh(void *opaque)
+{
+ VirtIONet *n = opaque;
+ int32_t ret;
+
+ assert(n->vdev.vm_running);
+
+ n->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);
+ 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;
+ 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;
+ }
+}
+
static void virtio_net_save(QEMUFile *f, void *opaque)
{
VirtIONet *n = opaque;
+ /* At this point, backend must be stopped, otherwise
+ * it might keep writing to memory. */
+ assert(!n->vhost_started);
virtio_save(&n->vdev, f);
qemu_put_buffer(f, n->mac, ETH_ALEN);
- qemu_put_be32(f, n->tx_timer_active);
+ qemu_put_be32(f, n->tx_waiting);
qemu_put_be32(f, n->mergeable_rx_bufs);
qemu_put_be16(f, n->status);
qemu_put_byte(f, n->promisc);
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, 0); /* vnet-hdr placeholder */
+ 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);
}
static int virtio_net_load(QEMUFile *f, void *opaque, int version_id)
virtio_load(&n->vdev, f);
qemu_get_buffer(f, n->mac, ETH_ALEN);
- n->tx_timer_active = qemu_get_be32(f);
+ n->tx_waiting = qemu_get_be32(f);
n->mergeable_rx_bufs = qemu_get_be32(f);
if (version_id >= 3)
if (version_id >= 6)
qemu_get_buffer(f, (uint8_t *)n->vlans, MAX_VLAN >> 3);
- if (version_id >= 7 && qemu_get_be32(f)) {
- fprintf(stderr,
- "virtio-net: saved image requires vnet header support\n");
- exit(1);
+ if (version_id >= 7) {
+ if (qemu_get_be32(f) && !peer_has_vnet_hdr(n)) {
+ error_report("virtio-net: saved image requires vnet_hdr=on");
+ return -1;
+ }
+
+ if (n->has_vnet_hdr) {
+ tap_using_vnet_hdr(n->nic->nc.peer, 1);
+ tap_set_offload(n->nic->nc.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,
+ (n->vdev.guest_features >> VIRTIO_NET_F_GUEST_ECN) & 1,
+ (n->vdev.guest_features >> VIRTIO_NET_F_GUEST_UFO) & 1);
+ }
}
if (version_id >= 9) {
n->nobcast = qemu_get_byte(f);
}
+ if (version_id >= 11) {
+ if (qemu_get_byte(f) && !peer_has_ufo(n)) {
+ error_report("virtio-net: saved image requires TUN_F_UFO support");
+ return -1;
+ }
+ }
+
/* 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) {
}
}
n->mac_table.first_multi = i;
-
- if (n->tx_timer_active) {
- qemu_mod_timer(n->tx_timer,
- qemu_get_clock(vm_clock) + TX_TIMER_INTERVAL);
- }
-
return 0;
}
-static void virtio_net_cleanup(VLANClientState *vc)
+static void virtio_net_cleanup(VLANClientState *nc)
{
- VirtIONet *n = vc->opaque;
-
- qemu_purge_queued_packets(vc);
-
- unregister_savevm("virtio-net", n);
-
- qemu_free(n->mac_table.macs);
- qemu_free(n->vlans);
-
- qemu_del_timer(n->tx_timer);
- qemu_free_timer(n->tx_timer);
+ VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
- virtio_cleanup(&n->vdev);
+ n->nic = NULL;
}
-VirtIODevice *virtio_net_init(DeviceState *dev)
+static NetClientInfo net_virtio_info = {
+ .type = NET_CLIENT_TYPE_NIC,
+ .size = sizeof(NICState),
+ .can_receive = virtio_net_can_receive,
+ .receive = virtio_net_receive,
+ .cleanup = virtio_net_cleanup,
+ .link_status_changed = virtio_net_set_link_status,
+};
+
+VirtIODevice *virtio_net_init(DeviceState *dev, NICConf *conf,
+ virtio_net_conf *net)
{
VirtIONet *n;
- static int virtio_net_id;
n = (VirtIONet *)virtio_common_init("virtio-net", VIRTIO_ID_NET,
sizeof(struct virtio_net_config),
n->vdev.set_features = virtio_net_set_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->tx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_tx);
+
+ if (net->tx && strcmp(net->tx, "timer") && strcmp(net->tx, "bh")) {
+ error_report("virtio-net: "
+ "Unknown option tx=%s, valid options: \"timer\" \"bh\"",
+ net->tx);
+ error_report("Defaulting to \"bh\"");
+ }
+
+ 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;
+ } 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->ctrl_vq = virtio_add_queue(&n->vdev, 64, virtio_net_handle_ctrl);
- qdev_get_macaddr(dev, n->mac);
+ qemu_macaddr_default_if_unset(&conf->macaddr);
+ memcpy(&n->mac[0], &conf->macaddr, sizeof(n->mac));
n->status = VIRTIO_NET_S_LINK_UP;
- n->vc = qdev_get_vlan_client(dev,
- virtio_net_can_receive,
- virtio_net_receive, NULL,
- virtio_net_cleanup, n);
- n->vc->link_status_changed = virtio_net_set_link_status;
- qemu_format_nic_info_str(n->vc, n->mac);
+ n->nic = qemu_new_nic(&net_virtio_info, conf, dev->info->name, dev->id, n);
- n->tx_timer = qemu_new_timer(vm_clock, virtio_net_tx_timer, n);
- n->tx_timer_active = 0;
+ qemu_format_nic_info_str(&n->nic->nc, conf->macaddr.a);
+
+ n->tx_waiting = 0;
+ n->tx_burst = net->txburst;
n->mergeable_rx_bufs = 0;
n->promisc = 1; /* for compatibility */
n->vlans = qemu_mallocz(MAX_VLAN >> 3);
- register_savevm("virtio-net", virtio_net_id++, VIRTIO_NET_VM_VERSION,
+ n->qdev = dev;
+ register_savevm(dev, "virtio-net", -1, VIRTIO_NET_VM_VERSION,
virtio_net_save, virtio_net_load, n);
+ add_boot_device_path(conf->bootindex, dev, "/ethernet-phy@0");
+
return &n->vdev;
}
+
+void virtio_net_exit(VirtIODevice *vdev)
+{
+ VirtIONet *n = DO_UPCAST(VirtIONet, vdev, vdev);
+
+ /* 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);
+
+ qemu_free(n->mac_table.macs);
+ qemu_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);
+ }
+
+ virtio_cleanup(&n->vdev);
+ qemu_del_vlan_client(&n->nic->nc);
+}
projects / qemu.git / blobdiff