[dpdk-dev,v4,3/3] net/virtio: support GUEST ANNOUNCE
Checks
Commit Message
When live migration is done, for the backup VM, either the virtio
frontend or the vhost backend needs to send out gratuitous RARP packet
to announce its new network location.
This patch enables VIRTIO_NET_F_GUEST_ANNOUNCE feature to support live
migration scenario where the vhost backend doesn't have the ability to
generate RARP packet.
Brief introduction of the work flow:
1. QEMU finishes live migration, pokes the backup VM with an interrupt.
2. Virtio interrupt handler reads out the interrupt status value, and
realizes it needs to send out RARP packet to announce its location.
3. Pause device to stop worker thread touching the queues.
4. Inject a RARP packet into a Tx Queue.
5. Ack the interrupt via control queue.
6. Resume device to continue packet processing.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
---
drivers/net/virtio/virtio_ethdev.c | 108 ++++++++++++++++++++++++++++++++++++-
drivers/net/virtio/virtio_ethdev.h | 1 +
drivers/net/virtio/virtqueue.h | 11 ++++
3 files changed, 118 insertions(+), 2 deletions(-)
Comments
On Thu, Jan 04, 2018 at 07:59:38AM -0800, Xiao Wang wrote:
[...]
> +static void
> +virtio_notify_peers(struct rte_eth_dev *dev)
> +{
> + struct virtio_hw *hw = dev->data->dev_private;
> + struct virtnet_tx *txvq = dev->data->tx_queues[0];
> + struct virtnet_rx *rxvq = dev->data->rx_queues[0];
> + struct rte_mbuf **rarp_buf;
> +
> + rarp_buf = rte_zmalloc("rarp_buf", sizeof(struct rte_mbuf *), 0);
> + if (!rarp_buf) {
> + PMD_INIT_LOG(ERR, "Failed to allocate rarp pointer");
> + return;
> + }
> +
> + rarp_buf[0] = rte_mbuf_raw_alloc(rxvq->mpool);
> + if (rarp_buf[0] == NULL) {
> + PMD_DRV_LOG(ERR, "first mbuf allocate free_bufed");
> + goto free_buf;
> + }
> +
> + if (make_rarp_packet(rarp_buf[0],
> + (struct ether_addr *)hw->mac_addr)) {
> + rte_pktmbuf_free(rarp_buf[0]);
> + goto free_buf;
> + }
> +
> + /* If virtio port just stopped, no need to send RARP */
> + if (virtio_dev_pause(dev) < 0) {
> + rte_pktmbuf_free(rarp_buf[0]);
> + goto free_buf;
> + }
> +
> + virtio_inject_pkts(dev, txvq, rarp_buf, 1);
You don't need to define rarp_buf as `struct rte_mbuf **`,
and dynamically alloc the mbuf pointer. You could alloc a
mbuf pointer on the stack directly, e.g.:
struct rte_mbuf *rarp_mbuf;
rarp_mbuf = rte_pktmbuf_alloc(...);
...
if (make_rarp_packet(rarp_mbuf, ...))
...
virtio_inject_pkts(..., &rarp_mbuf, 1);
Thanks,
Tiwei
@@ -48,6 +48,8 @@
#include <rte_pci.h>
#include <rte_bus_pci.h>
#include <rte_ether.h>
+#include <rte_ip.h>
+#include <rte_arp.h>
#include <rte_common.h>
#include <rte_errno.h>
#include <rte_cpuflags.h>
@@ -107,6 +109,11 @@ static int virtio_dev_queue_stats_mapping_set(
uint8_t stat_idx,
uint8_t is_rx);
+static int make_rarp_packet(struct rte_mbuf *rarp_mbuf,
+ const struct ether_addr *mac);
+static void virtio_notify_peers(struct rte_eth_dev *dev);
+static void virtio_ack_link_announce(struct rte_eth_dev *dev);
+
/*
* The set of PCI devices this driver supports
*/
@@ -1289,9 +1296,102 @@ static int virtio_dev_xstats_get_names(struct rte_eth_dev *dev,
dev->tx_pkt_burst(txvq, buf, count);
}
+#define RARP_PKT_SIZE 64
+static int
+make_rarp_packet(struct rte_mbuf *rarp_mbuf, const struct ether_addr *mac)
+{
+ struct ether_hdr *eth_hdr;
+ struct arp_hdr *rarp;
+
+ if (rarp_mbuf->buf_len < RARP_PKT_SIZE) {
+ PMD_DRV_LOG(ERR, "mbuf size too small %u (< %d)",
+ rarp_mbuf->buf_len, RARP_PKT_SIZE);
+ return -1;
+ }
+
+ /* Ethernet header. */
+ eth_hdr = rte_pktmbuf_mtod(rarp_mbuf, struct ether_hdr *);
+ memset(eth_hdr->d_addr.addr_bytes, 0xff, ETHER_ADDR_LEN);
+ ether_addr_copy(mac, ð_hdr->s_addr);
+ eth_hdr->ether_type = htons(ETHER_TYPE_RARP);
+
+ /* RARP header. */
+ rarp = (struct arp_hdr *)(eth_hdr + 1);
+ rarp->arp_hrd = htons(ARP_HRD_ETHER);
+ rarp->arp_pro = htons(ETHER_TYPE_IPv4);
+ rarp->arp_hln = ETHER_ADDR_LEN;
+ rarp->arp_pln = 4;
+ rarp->arp_op = htons(ARP_OP_REVREQUEST);
+
+ ether_addr_copy(mac, &rarp->arp_data.arp_sha);
+ ether_addr_copy(mac, &rarp->arp_data.arp_tha);
+ memset(&rarp->arp_data.arp_sip, 0x00, 4);
+ memset(&rarp->arp_data.arp_tip, 0x00, 4);
+
+ rarp_mbuf->data_len = RARP_PKT_SIZE;
+ rarp_mbuf->pkt_len = RARP_PKT_SIZE;
+
+ return 0;
+}
+
+static void
+virtio_notify_peers(struct rte_eth_dev *dev)
+{
+ struct virtio_hw *hw = dev->data->dev_private;
+ struct virtnet_tx *txvq = dev->data->tx_queues[0];
+ struct virtnet_rx *rxvq = dev->data->rx_queues[0];
+ struct rte_mbuf **rarp_buf;
+
+ rarp_buf = rte_zmalloc("rarp_buf", sizeof(struct rte_mbuf *), 0);
+ if (!rarp_buf) {
+ PMD_INIT_LOG(ERR, "Failed to allocate rarp pointer");
+ return;
+ }
+
+ rarp_buf[0] = rte_mbuf_raw_alloc(rxvq->mpool);
+ if (rarp_buf[0] == NULL) {
+ PMD_DRV_LOG(ERR, "first mbuf allocate free_bufed");
+ goto free_buf;
+ }
+
+ if (make_rarp_packet(rarp_buf[0],
+ (struct ether_addr *)hw->mac_addr)) {
+ rte_pktmbuf_free(rarp_buf[0]);
+ goto free_buf;
+ }
+
+ /* If virtio port just stopped, no need to send RARP */
+ if (virtio_dev_pause(dev) < 0) {
+ rte_pktmbuf_free(rarp_buf[0]);
+ goto free_buf;
+ }
+
+ virtio_inject_pkts(dev, txvq, rarp_buf, 1);
+ /* Recover the stored hw status to let worker thread continue */
+ virtio_dev_resume(dev);
+
+free_buf:
+ rte_free(rarp_buf);
+}
+
+static void
+virtio_ack_link_announce(struct rte_eth_dev *dev)
+{
+ struct virtio_hw *hw = dev->data->dev_private;
+ struct virtio_pmd_ctrl ctrl;
+ int len;
+
+ ctrl.hdr.class = VIRTIO_NET_CTRL_ANNOUNCE;
+ ctrl.hdr.cmd = VIRTIO_NET_CTRL_ANNOUNCE_ACK;
+ len = 0;
+
+ virtio_send_command(hw->cvq, &ctrl, &len, 0);
+}
+
/*
- * Process Virtio Config changed interrupt and call the callback
- * if link state changed.
+ * Process virtio config changed interrupt. Call the callback
+ * if link state changed, generate gratuitous RARP packet if
+ * the status indicates an ANNOUNCE.
*/
void
virtio_interrupt_handler(void *param)
@@ -1314,6 +1414,10 @@ static int virtio_dev_xstats_get_names(struct rte_eth_dev *dev,
NULL, NULL);
}
+ if (isr & VIRTIO_NET_S_ANNOUNCE) {
+ virtio_notify_peers(dev);
+ virtio_ack_link_announce(dev);
+ }
}
/* set rx and tx handlers according to what is supported */
@@ -68,6 +68,7 @@
1u << VIRTIO_NET_F_HOST_TSO6 | \
1u << VIRTIO_NET_F_MRG_RXBUF | \
1u << VIRTIO_NET_F_MTU | \
+ 1ULL << VIRTIO_NET_F_GUEST_ANNOUNCE | \
1u << VIRTIO_RING_F_INDIRECT_DESC | \
1ULL << VIRTIO_F_VERSION_1 | \
1ULL << VIRTIO_F_IOMMU_PLATFORM)
@@ -158,6 +158,17 @@ struct virtio_net_ctrl_mac {
#define VIRTIO_NET_CTRL_VLAN_ADD 0
#define VIRTIO_NET_CTRL_VLAN_DEL 1
+/*
+ * Control link announce acknowledgement
+ *
+ * The command VIRTIO_NET_CTRL_ANNOUNCE_ACK is used to indicate that
+ * driver has recevied the notification; device would clear the
+ * VIRTIO_NET_S_ANNOUNCE bit in the status field after it receives
+ * this command.
+ */
+#define VIRTIO_NET_CTRL_ANNOUNCE 3
+#define VIRTIO_NET_CTRL_ANNOUNCE_ACK 0
+
struct virtio_net_ctrl_hdr {
uint8_t class;
uint8_t cmd;