net/af_packet: reinsert stripped VLAN tag

The af_packet pmd driver binds to a raw socket and allows sending and
receiving of packets through the kernel.

Since commit [1], the kernel strips the vlan tags early in
__netif_receive_skb_core(), so we receive untagged packets while running
with the af_packet pmd.

Luckily for us, the skb vlan-related fields are still populated from the
stripped vlan tags, so we end up having all the information that we need
in the mbuf.

Having the pmd driver support DEV_RX_OFFLOAD_VLAN_STRIP allows the
application to control the desired vlan stripping behavior, until we
have a way to describe offloads that can't be disabled by pmd drivers.

This patch will cause a change in the default way that the af_packet pmd
treats received vlan-tagged frames. While previously, the application
was required to check the PKT_RX_VLAN_STRIPPED flag, after this patch,
the pmd will re-insert the vlan tag transparently to the user, unless
the DEV_RX_OFFLOAD_VLAN_STRIP is enabled in rxmode.offloads.

I've attempted a preliminary benchmark to understand if the change could
cause a sizable performance hit.

Setup:
Two virtual machines running on top of an ESXi hypervisor

Tx: DPDK app (running on top of vmxnet3 PMD)
Rx: af_packet (running on top of a kernel vmxnet3 interface)
Packet size :68 (packet contains a vlan tag)

Rates:
Tx - 1.419 Mpps
Rx (without vlan insertion) - 1227636 pps
Rx (with vlan insertion)    - 1220081 pps

At a first glance, we don't seem to have a large degradation in terms of
packet rate.

[1]
https://github.com/torvalds/linux/commit/bcc6d47903612c3861201cc3a866fb60

Signed-off-by: Tudor Cornea <tudor.cornea@gmail.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>

doc/guides/nics/af_packet.rst

@@ -65,3 +65,10 @@ framecnt=512):
 .. code-block:: console
 
     --vdev=eth_af_packet0,iface=tap0,blocksz=4096,framesz=2048,framecnt=512,qpairs=1,qdisc_bypass=0
+
+Features and Limitations
+------------------------
+
+The PMD will re-insert the VLAN tag transparently to the packet if the kernel
+strips it, as long as the ``DEV_RX_OFFLOAD_VLAN_STRIP`` is not enabled by the
+application.

doc/guides/rel_notes/release_21_11.rst

@@ -67,6 +67,11 @@ New Features
   Added macros ETH_RSS_IPV4_CHKSUM and ETH_RSS_L4_CHKSUM, now IPv4 and
   TCP/UDP/SCTP header checksum field can be used as input set for RSS.
 
+* **Updated af_packet ethdev driver.**
+
+  * Default VLAN strip behavior was changed. VLAN tag won't be stripped
+    unless ``DEV_RX_OFFLOAD_VLAN_STRIP`` offload is enabled.
+
 * **Updated Broadcom bnxt PMD.**
 
   * Added flow offload support for Thor.

drivers/net/af_packet/rte_eth_af_packet.c

@@ -48,6 +48,7 @@ struct pkt_rx_queue {
 
 	struct rte_mempool *mb_pool;
 	uint16_t in_port;
+	uint8_t vlan_strip;
 
 	volatile unsigned long rx_pkts;
 	volatile unsigned long rx_bytes;
@@ -78,6 +79,7 @@ struct pmd_internals {
 
 	struct pkt_rx_queue *rx_queue;
 	struct pkt_tx_queue *tx_queue;
+	uint8_t vlan_strip;
 };
 
 static const char *valid_arguments[] = {
@@ -148,6 +150,9 @@ eth_af_packet_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 		if (ppd->tp_status & TP_STATUS_VLAN_VALID) {
 			mbuf->vlan_tci = ppd->tp_vlan_tci;
 			mbuf->ol_flags |= (PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED);
+
+			if (!pkt_q->vlan_strip && rte_vlan_insert(&mbuf))
+				PMD_LOG(ERR, "Failed to reinsert VLAN tag");
 		}
 
 		/* release incoming frame and advance ring buffer */
@@ -322,6 +327,11 @@ eth_dev_stop(struct rte_eth_dev *dev)
 static int
 eth_dev_configure(struct rte_eth_dev *dev __rte_unused)
 {
+	struct rte_eth_conf *dev_conf = &dev->data->dev_conf;
+	const struct rte_eth_rxmode *rxmode = &dev_conf->rxmode;
+	struct pmd_internals *internals = dev->data->dev_private;
+
+	internals->vlan_strip = !!(rxmode->offloads & DEV_RX_OFFLOAD_VLAN_STRIP);
 	return 0;
 }
 
@@ -338,6 +348,7 @@ eth_dev_info(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 	dev_info->min_rx_bufsize = 0;
 	dev_info->tx_offload_capa = DEV_TX_OFFLOAD_MULTI_SEGS |
 		DEV_TX_OFFLOAD_VLAN_INSERT;
+	dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP;
 
 	return 0;
 }
@@ -468,6 +479,7 @@ eth_rx_queue_setup(struct rte_eth_dev *dev,
 
 	dev->data->rx_queues[rx_queue_id] = pkt_q;
 	pkt_q->in_port = dev->data->port_id;
+	pkt_q->vlan_strip = internals->vlan_strip;
 
 	return 0;
 }