[dpdk-dev] [PATCH v6 3/3] net/virtio: support GUEST ANNOUNCE

[Xiao Wang]

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 at intel.com>
---
 drivers/net/virtio/virtio_ethdev.c | 95 +++++++++++++++++++++++++++++++++++++-
 drivers/net/virtio/virtio_ethdev.h |  1 +
 drivers/net/virtio/virtqueue.h     | 11 +++++
 3 files changed, 105 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c
index 8f64220b0..4174da186 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++ b/drivers/net/virtio/virtio_ethdev.c
@@ -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
  */
@@ -1301,9 +1308,89 @@ virtio_inject_pkts(struct rte_eth_dev *dev, struct rte_mbuf **tx_pkts,
 	return ret;
 }
 
+#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, &eth_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_rx *rxvq = dev->data->rx_queues[0];
+	struct rte_mbuf *rarp_mbuf;
+
+	rarp_mbuf = rte_pktmbuf_alloc(rxvq->mpool);
+	if (rarp_mbuf == NULL) {
+		PMD_DRV_LOG(ERR, "mbuf allocate failed");
+		return;
+	}
+
+	if (make_rarp_packet(rarp_mbuf,
+			(struct ether_addr *)hw->mac_addr) < 0) {
+		rte_pktmbuf_free(rarp_mbuf);
+		return;
+	}
+
+	/* If virtio port just stopped, no need to send RARP */
+	if (virtio_dev_pause(dev) < 0) {
+		rte_pktmbuf_free(rarp_mbuf);
+		return;
+	}
+
+	virtio_inject_pkts(dev, &rarp_mbuf, 1);
+	virtio_dev_resume(dev);
+}
+
+static void
+virtio_ack_link_announce(struct rte_eth_dev *dev)
+{
+	struct virtio_hw *hw = dev->data->dev_private;
+	struct virtio_pmd_ctrl ctrl;
+
+	ctrl.hdr.class = VIRTIO_NET_CTRL_ANNOUNCE;
+	ctrl.hdr.cmd = VIRTIO_NET_CTRL_ANNOUNCE_ACK;
+
+	virtio_send_command(hw->cvq, &ctrl, NULL, 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)
@@ -1326,6 +1413,10 @@ virtio_interrupt_handler(void *param)
 						      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 */
diff --git a/drivers/net/virtio/virtio_ethdev.h b/drivers/net/virtio/virtio_ethdev.h
index 6b0c4f9af..5bc5d9385 100644
--- a/drivers/net/virtio/virtio_ethdev.h
+++ b/drivers/net/virtio/virtio_ethdev.h
@@ -67,6 +67,7 @@
 	 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)
diff --git a/drivers/net/virtio/virtqueue.h b/drivers/net/virtio/virtqueue.h
index 2305d91a4..d9045e156 100644
--- a/drivers/net/virtio/virtqueue.h
+++ b/drivers/net/virtio/virtqueue.h
@@ -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;
-- 
2.15.1