#include "virtio.h"
#include "net.h"
+#include "net/checksum.h"
+#include "net/tap.h"
#include "qemu-timer.h"
#include "virtio-net.h"
-#define VIRTIO_NET_VM_VERSION 6
+#define VIRTIO_NET_VM_VERSION 11
-#define MAC_TABLE_ENTRIES 32
+#define MAC_TABLE_ENTRIES 64
#define MAX_VLAN (1 << 12) /* Per 802.1Q definition */
typedef struct VirtIONet
VirtQueue *rx_vq;
VirtQueue *tx_vq;
VirtQueue *ctrl_vq;
- VLANClientState *vc;
+ NICState *nic;
QEMUTimer *tx_timer;
int tx_timer_active;
+ uint32_t has_vnet_hdr;
+ uint8_t has_ufo;
+ struct {
+ VirtQueueElement elem;
+ ssize_t len;
+ } async_tx;
int mergeable_rx_bufs;
- int promisc;
- int allmulti;
+ uint8_t promisc;
+ uint8_t allmulti;
+ uint8_t alluni;
+ uint8_t nomulti;
+ uint8_t nouni;
+ uint8_t nobcast;
struct {
int in_use;
+ int first_multi;
+ uint8_t multi_overflow;
+ uint8_t uni_overflow;
uint8_t *macs;
} mac_table;
uint32_t *vlans;
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 void virtio_net_set_link_status(VLANClientState *nc)
{
- VirtIONet *n = vc->opaque;
+ 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;
/* Reset back to compatibility mode */
n->promisc = 1;
n->allmulti = 0;
+ n->alluni = 0;
+ n->nomulti = 0;
+ n->nouni = 0;
+ n->nobcast = 0;
/* Flush any MAC and VLAN filter table state */
n->mac_table.in_use = 0;
+ n->mac_table.first_multi = 0;
+ n->mac_table.multi_overflow = 0;
+ n->mac_table.uni_overflow = 0;
memset(n->mac_table.macs, 0, MAC_TABLE_ENTRIES * ETH_ALEN);
memset(n->vlans, 0, MAX_VLAN >> 3);
}
-static uint32_t virtio_net_get_features(VirtIODevice *vdev)
+static int peer_has_vnet_hdr(VirtIONet *n)
+{
+ if (!n->nic->nc.peer)
+ return 0;
+
+ 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)
{
- uint32_t features = (1 << VIRTIO_NET_F_MAC) |
- (1 << VIRTIO_NET_F_STATUS) |
- (1 << VIRTIO_NET_F_CTRL_VQ) |
- (1 << VIRTIO_NET_F_CTRL_RX) |
- (1 << VIRTIO_NET_F_CTRL_VLAN);
+ 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);
+ }
return features;
}
/* 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);
+ }
}
static int virtio_net_handle_rx_mode(VirtIONet *n, uint8_t cmd,
n->promisc = on;
else if (cmd == VIRTIO_NET_CTRL_RX_MODE_ALLMULTI)
n->allmulti = on;
+ else if (cmd == VIRTIO_NET_CTRL_RX_MODE_ALLUNI)
+ n->alluni = on;
+ else if (cmd == VIRTIO_NET_CTRL_RX_MODE_NOMULTI)
+ n->nomulti = on;
+ else if (cmd == VIRTIO_NET_CTRL_RX_MODE_NOUNI)
+ n->nouni = on;
+ else if (cmd == VIRTIO_NET_CTRL_RX_MODE_NOBCAST)
+ n->nobcast = on;
else
return VIRTIO_NET_ERR;
return VIRTIO_NET_ERR;
n->mac_table.in_use = 0;
+ n->mac_table.first_multi = 0;
+ n->mac_table.uni_overflow = 0;
+ 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 * ETH_ALEN);
n->mac_table.in_use += mac_data.entries;
} else {
- n->promisc = 1;
- return VIRTIO_NET_OK;
+ n->mac_table.uni_overflow = 1;
}
+ n->mac_table.first_multi = n->mac_table.in_use;
+
mac_data.entries = ldl_le_p(elem->out_sg[2].iov_base);
if (sizeof(mac_data.entries) +
elem->out_sg[2].iov_base + sizeof(mac_data),
mac_data.entries * ETH_ALEN);
n->mac_table.in_use += mac_data.entries;
- } else
- n->allmulti = 1;
+ } else {
+ n->mac_table.multi_overflow = 1;
+ }
}
return VIRTIO_NET_OK;
static void virtio_net_handle_rx(VirtIODevice *vdev, VirtQueue *vq)
{
+ VirtIONet *n = to_virtio_net(vdev);
+
+ 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 (!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))) {
return 1;
}
-static int virtio_net_can_receive(VLANClientState *vc)
+/* 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)
{
- VirtIONet *n = vc->opaque;
-
- return do_virtio_net_can_receive(n, VIRTIO_NET_MAX_BUFSIZE);
+ 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;
+ }
}
static int iov_fill(struct iovec *iov, int iovcnt, const void *buf, int count)
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;
}
- if ((ptr[0] & 1) && n->allmulti)
- return 1;
-
- if (!memcmp(ptr, bcast, sizeof(bcast)))
- return 1;
-
- if (!memcmp(ptr, n->mac, ETH_ALEN))
- return 1;
+ if (ptr[0] & 1) { // multicast
+ if (!memcmp(ptr, bcast, sizeof(bcast))) {
+ return !n->nobcast;
+ } else if (n->nomulti) {
+ return 0;
+ } else if (n->allmulti || n->mac_table.multi_overflow) {
+ return 1;
+ }
- for (i = 0; i < n->mac_table.in_use; i++) {
- if (!memcmp(ptr, &n->mac_table.macs[i * ETH_ALEN], ETH_ALEN))
+ for (i = n->mac_table.first_multi; i < n->mac_table.in_use; i++) {
+ if (!memcmp(ptr, &n->mac_table.macs[i * ETH_ALEN], ETH_ALEN)) {
+ return 1;
+ }
+ }
+ } else { // unicast
+ if (n->nouni) {
+ return 0;
+ } else if (n->alluni || n->mac_table.uni_overflow) {
return 1;
+ } else if (!memcmp(ptr, n->mac, ETH_ALEN)) {
+ return 1;
+ }
+
+ for (i = 0; i < n->mac_table.first_multi; i++) {
+ if (!memcmp(ptr, &n->mac_table.macs[i * ETH_ALEN], ETH_ALEN)) {
+ return 1;
+ }
+ }
}
return 0;
}
-static void 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;
- if (!do_virtio_net_can_receive(n, size))
- return;
+ if (!virtio_net_can_receive(&n->nic->nc))
+ return -1;
+
+ if (!virtio_net_has_buffers(n, size))
+ return 0;
if (!receive_filter(n, buf, size))
- return;
+ return size;
/* hdr_len refers to the header we supply to the guest */
hdr_len = n->mergeable_rx_bufs ?
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 (i == 0)
- return;
+ return -1;
fprintf(stderr, "virtio-net truncating packet\n");
exit(1);
}
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 void virtio_net_tx_complete(VLANClientState *nc, ssize_t len)
+{
+ 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);
+
+ n->async_tx.elem.out_num = n->async_tx.len = 0;
+
+ virtio_queue_set_notification(n->tx_vq, 1);
+ virtio_net_flush_tx(n, n->tx_vq);
}
/* TX */
static void virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq)
{
VirtQueueElement elem;
- int has_vnet_hdr = 0;
if (!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK))
return;
+ if (n->async_tx.elem.out_num) {
+ virtio_queue_set_notification(n->tx_vq, 0);
+ return;
+ }
+
while (virtqueue_pop(vq, &elem)) {
- ssize_t len = 0;
+ ssize_t ret, len = 0;
unsigned int out_num = elem.out_num;
struct iovec *out_sg = &elem.out_sg[0];
unsigned hdr_len;
}
/* 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;
}
- len += qemu_sendv_packet(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;
+ }
+
+ len += ret;
virtqueue_push(vq, &elem, len);
virtio_notify(&n->vdev, vq);
qemu_put_be32(f, n->tx_timer_active);
qemu_put_be32(f, n->mergeable_rx_bufs);
qemu_put_be16(f, n->status);
- qemu_put_be32(f, n->promisc);
- qemu_put_be32(f, n->allmulti);
+ 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);
}
static int virtio_net_load(QEMUFile *f, void *opaque, int version_id)
{
VirtIONet *n = opaque;
+ int i;
if (version_id < 2 || version_id > VIRTIO_NET_VM_VERSION)
return -EINVAL;
n->status = qemu_get_be16(f);
if (version_id >= 4) {
- n->promisc = qemu_get_be32(f);
- n->allmulti = qemu_get_be32(f);
+ if (version_id < 8) {
+ n->promisc = qemu_get_be32(f);
+ n->allmulti = qemu_get_be32(f);
+ } else {
+ n->promisc = qemu_get_byte(f);
+ n->allmulti = qemu_get_byte(f);
+ }
}
if (version_id >= 5) {
n->mac_table.in_use * ETH_ALEN);
} else if (n->mac_table.in_use) {
qemu_fseek(f, n->mac_table.in_use * ETH_ALEN, SEEK_CUR);
- n->promisc = 1;
+ n->mac_table.multi_overflow = n->mac_table.uni_overflow = 1;
n->mac_table.in_use = 0;
}
}
if (version_id >= 6)
qemu_get_buffer(f, (uint8_t *)n->vlans, MAX_VLAN >> 3);
+ if (version_id >= 7) {
+ if (qemu_get_be32(f) && !peer_has_vnet_hdr(n)) {
+ qemu_error("virtio-net: saved image requires vnet_hdr=on\n");
+ 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->mac_table.multi_overflow = qemu_get_byte(f);
+ n->mac_table.uni_overflow = qemu_get_byte(f);
+ }
+
+ if (version_id >= 10) {
+ 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 (version_id >= 11) {
+ if (qemu_get_byte(f) && !peer_has_ufo(n)) {
+ qemu_error("virtio-net: saved image requires TUN_F_UFO support\n");
+ 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) {
+ break;
+ }
+ }
+ 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;
-
- unregister_savevm("virtio-net", n);
+ VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
- qemu_free(n->mac_table.macs);
- qemu_free(n->vlans);
-
- qemu_del_timer(n->tx_timer);
- qemu_free_timer(n->tx_timer);
-
- 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)
{
VirtIONet *n;
static int virtio_net_id;
n->vdev.reset = virtio_net_reset;
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);
- n->ctrl_vq = virtio_add_queue(&n->vdev, 16, virtio_net_handle_ctrl);
- qdev_get_macaddr(dev, n->mac);
+ n->ctrl_vq = virtio_add_queue(&n->vdev, 64, virtio_net_handle_ctrl);
+ 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);
+
+ qemu_format_nic_info_str(&n->nic->nc, conf->macaddr.a);
n->tx_timer = qemu_new_timer(vm_clock, virtio_net_tx_timer, n);
n->tx_timer_active = 0;
return &n->vdev;
}
+
+void virtio_net_exit(VirtIODevice *vdev)
+{
+ VirtIONet *n = DO_UPCAST(VirtIONet, vdev, vdev);
+
+ qemu_purge_queued_packets(&n->nic->nc);
+
+ 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);
+
+ virtio_cleanup(&n->vdev);
+ qemu_del_vlan_client(&n->nic->nc);
+}
projects / qemu.git / blobdiff