[PATCH v7] app/testpmd: expand noisy neighbour forward mode support

[Mike Pattrick <mkp@redhat.com>]

Previously the noisy neighbour vnf simulation would only operate in io
mode, forwarding packets as is. However, this limited the usefulness of
noisy neighbour simulation.

This feature has now been expanded to supporting mac, macswap, and
5tswap modes. To facilitate adding this support, some new header files
were added.

Signed-off-by: Mike Pattrick <mkp@redhat.com>
 ---
 v2: Reverted changes to random memory lookup
 v3: Refactored entire patch
 v4: Implemented recommended formatting changes
 v5: Corrected copyright statement and formatting changes
 v6: Reordered some variables, preserved noisy subtype for display
 v7: Made fwd engine status generic across all modules
---
 app/test-pmd/5tswap.c                 | 118 +----------------------
 app/test-pmd/5tswap.h                 | 130 ++++++++++++++++++++++++++
 app/test-pmd/config.c                 |  18 +++-
 app/test-pmd/macfwd.c                 |  33 +------
 app/test-pmd/macfwd.h                 |  45 +++++++++
 app/test-pmd/noisy_vnf.c              | 113 ++++++++++++++++++----
 app/test-pmd/parameters.c             |  15 +++
 app/test-pmd/testpmd.c                |  14 +++
 app/test-pmd/testpmd.h                |  11 +++
 doc/guides/testpmd_app_ug/run_app.rst |   9 ++
 10 files changed, 342 insertions(+), 164 deletions(-)
 create mode 100644 app/test-pmd/5tswap.h
 create mode 100644 app/test-pmd/macfwd.h

diff --git a/app/test-pmd/5tswap.c b/app/test-pmd/5tswap.c
index ff8c2dcde5..8e8de2557a 100644
--- a/app/test-pmd/5tswap.c
+++ b/app/test-pmd/5tswap.c
@@ -17,64 +17,8 @@
 #include <rte_ip.h>
 #include <rte_flow.h>
 
-#include "macswap_common.h"
 #include "testpmd.h"
-
-
-static inline void
-swap_mac(struct rte_ether_hdr *eth_hdr)
-{
-	struct rte_ether_addr addr;
-
-	/* Swap dest and src mac addresses. */
-	rte_ether_addr_copy(&eth_hdr->dst_addr, &addr);
-	rte_ether_addr_copy(&eth_hdr->src_addr, &eth_hdr->dst_addr);
-	rte_ether_addr_copy(&addr, &eth_hdr->src_addr);
-}
-
-static inline void
-swap_ipv4(struct rte_ipv4_hdr *ipv4_hdr)
-{
-	rte_be32_t addr;
-
-	/* Swap dest and src ipv4 addresses. */
-	addr = ipv4_hdr->src_addr;
-	ipv4_hdr->src_addr = ipv4_hdr->dst_addr;
-	ipv4_hdr->dst_addr = addr;
-}
-
-static inline void
-swap_ipv6(struct rte_ipv6_hdr *ipv6_hdr)
-{
-	uint8_t addr[16];
-
-	/* Swap dest and src ipv6 addresses. */
-	memcpy(&addr, &ipv6_hdr->src_addr, 16);
-	memcpy(&ipv6_hdr->src_addr, &ipv6_hdr->dst_addr, 16);
-	memcpy(&ipv6_hdr->dst_addr, &addr, 16);
-}
-
-static inline void
-swap_tcp(struct rte_tcp_hdr *tcp_hdr)
-{
-	rte_be16_t port;
-
-	/* Swap dest and src tcp port. */
-	port = tcp_hdr->src_port;
-	tcp_hdr->src_port = tcp_hdr->dst_port;
-	tcp_hdr->dst_port = port;
-}
-
-static inline void
-swap_udp(struct rte_udp_hdr *udp_hdr)
-{
-	rte_be16_t port;
-
-	/* Swap dest and src udp port */
-	port = udp_hdr->src_port;
-	udp_hdr->src_port = udp_hdr->dst_port;
-	udp_hdr->dst_port = port;
-}
+#include "5tswap.h"
 
 /*
  * 5 tuple swap forwarding mode: Swap the source and the destination of layers
@@ -85,22 +29,7 @@ static bool
 pkt_burst_5tuple_swap(struct fwd_stream *fs)
 {
 	struct rte_mbuf  *pkts_burst[MAX_PKT_BURST];
-	struct rte_port  *txp;
-	struct rte_mbuf *mb;
-	uint16_t next_proto;
-	uint64_t ol_flags;
-	uint16_t proto;
 	uint16_t nb_rx;
-	int i;
-	union {
-		struct rte_ether_hdr *eth;
-		struct rte_vlan_hdr *vlan;
-		struct rte_ipv4_hdr *ipv4;
-		struct rte_ipv6_hdr *ipv6;
-		struct rte_tcp_hdr *tcp;
-		struct rte_udp_hdr *udp;
-		uint8_t *byte;
-	} h;
 
 	/*
 	 * Receive a burst of packets and forward them.
@@ -109,49 +38,8 @@ pkt_burst_5tuple_swap(struct fwd_stream *fs)
 	if (unlikely(nb_rx == 0))
 		return false;
 
-	txp = &ports[fs->tx_port];
-	ol_flags = ol_flags_init(txp->dev_conf.txmode.offloads);
-	vlan_qinq_set(pkts_burst, nb_rx, ol_flags,
-			txp->tx_vlan_id, txp->tx_vlan_id_outer);
-	for (i = 0; i < nb_rx; i++) {
-		if (likely(i < nb_rx - 1))
-			rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i+1],
-					void *));
-		mb = pkts_burst[i];
-		h.eth = rte_pktmbuf_mtod(mb, struct rte_ether_hdr *);
-		proto = h.eth->ether_type;
-		swap_mac(h.eth);
-		mb->l2_len = sizeof(struct rte_ether_hdr);
-		h.eth++;
-		while (proto == RTE_BE16(RTE_ETHER_TYPE_VLAN) ||
-		       proto == RTE_BE16(RTE_ETHER_TYPE_QINQ)) {
-			proto = h.vlan->eth_proto;
-			h.vlan++;
-			mb->l2_len += sizeof(struct rte_vlan_hdr);
-		}
-		if (proto == RTE_BE16(RTE_ETHER_TYPE_IPV4)) {
-			swap_ipv4(h.ipv4);
-			next_proto = h.ipv4->next_proto_id;
-			mb->l3_len = rte_ipv4_hdr_len(h.ipv4);
-			h.byte += mb->l3_len;
-		} else if (proto == RTE_BE16(RTE_ETHER_TYPE_IPV6)) {
-			swap_ipv6(h.ipv6);
-			next_proto = h.ipv6->proto;
-			h.ipv6++;
-			mb->l3_len = sizeof(struct rte_ipv6_hdr);
-		} else {
-			mbuf_field_set(mb, ol_flags);
-			continue;
-		}
-		if (next_proto == IPPROTO_UDP) {
-			swap_udp(h.udp);
-			mb->l4_len = sizeof(struct rte_udp_hdr);
-		} else if (next_proto == IPPROTO_TCP) {
-			swap_tcp(h.tcp);
-			mb->l4_len = (h.tcp->data_off & 0xf0) >> 2;
-		}
-		mbuf_field_set(mb, ol_flags);
-	}
+	do_5tswap(pkts_burst, nb_rx, fs);
+
 	common_fwd_stream_transmit(fs, pkts_burst, nb_rx);
 
 	return true;
diff --git a/app/test-pmd/5tswap.h b/app/test-pmd/5tswap.h
new file mode 100644
index 0000000000..345c08b4d0
--- /dev/null
+++ b/app/test-pmd/5tswap.h
@@ -0,0 +1,130 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2014-2020 Mellanox Technologies, Ltd
+ */
+
+#ifndef _5TSWAP_H_
+#define _5TSWAP_H_
+
+#include "macswap_common.h"
+
+static inline void
+swap_mac(struct rte_ether_hdr *eth_hdr)
+{
+	struct rte_ether_addr addr;
+
+	/* Swap dest and src mac addresses. */
+	rte_ether_addr_copy(&eth_hdr->dst_addr, &addr);
+	rte_ether_addr_copy(&eth_hdr->src_addr, &eth_hdr->dst_addr);
+	rte_ether_addr_copy(&addr, &eth_hdr->src_addr);
+}
+
+static inline void
+swap_ipv4(struct rte_ipv4_hdr *ipv4_hdr)
+{
+	rte_be32_t addr;
+
+	/* Swap dest and src ipv4 addresses. */
+	addr = ipv4_hdr->src_addr;
+	ipv4_hdr->src_addr = ipv4_hdr->dst_addr;
+	ipv4_hdr->dst_addr = addr;
+}
+
+static inline void
+swap_ipv6(struct rte_ipv6_hdr *ipv6_hdr)
+{
+	uint8_t addr[16];
+
+	/* Swap dest and src ipv6 addresses. */
+	memcpy(&addr, &ipv6_hdr->src_addr, 16);
+	memcpy(&ipv6_hdr->src_addr, &ipv6_hdr->dst_addr, 16);
+	memcpy(&ipv6_hdr->dst_addr, &addr, 16);
+}
+
+static inline void
+swap_tcp(struct rte_tcp_hdr *tcp_hdr)
+{
+	rte_be16_t port;
+
+	/* Swap dest and src tcp port. */
+	port = tcp_hdr->src_port;
+	tcp_hdr->src_port = tcp_hdr->dst_port;
+	tcp_hdr->dst_port = port;
+}
+
+static inline void
+swap_udp(struct rte_udp_hdr *udp_hdr)
+{
+	rte_be16_t port;
+
+	/* Swap dest and src udp port */
+	port = udp_hdr->src_port;
+	udp_hdr->src_port = udp_hdr->dst_port;
+	udp_hdr->dst_port = port;
+}
+
+static inline void
+do_5tswap(struct rte_mbuf *pkts_burst[], uint16_t nb_rx,
+	  struct fwd_stream *fs)
+{
+	struct rte_port  *txp;
+	struct rte_mbuf *mb;
+	uint16_t next_proto;
+	uint64_t ol_flags;
+	uint16_t proto;
+	int i;
+	union {
+		struct rte_ether_hdr *eth;
+		struct rte_vlan_hdr *vlan;
+		struct rte_ipv4_hdr *ipv4;
+		struct rte_ipv6_hdr *ipv6;
+		struct rte_tcp_hdr *tcp;
+		struct rte_udp_hdr *udp;
+		uint8_t *byte;
+	} h;
+
+	txp = &ports[fs->tx_port];
+	ol_flags = ol_flags_init(txp->dev_conf.txmode.offloads);
+	vlan_qinq_set(pkts_burst, nb_rx, ol_flags,
+		      txp->tx_vlan_id, txp->tx_vlan_id_outer);
+	for (i = 0; i < nb_rx; i++) {
+		if (likely(i < nb_rx - 1))
+			rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i+1],
+						       void *));
+		mb = pkts_burst[i];
+		h.eth = rte_pktmbuf_mtod(mb, struct rte_ether_hdr *);
+		proto = h.eth->ether_type;
+		swap_mac(h.eth);
+		mb->l2_len = sizeof(struct rte_ether_hdr);
+		h.eth++;
+		while (proto == RTE_BE16(RTE_ETHER_TYPE_VLAN) ||
+		       proto == RTE_BE16(RTE_ETHER_TYPE_QINQ)) {
+			proto = h.vlan->eth_proto;
+			h.vlan++;
+			mb->l2_len += sizeof(struct rte_vlan_hdr);
+		}
+		if (proto == RTE_BE16(RTE_ETHER_TYPE_IPV4)) {
+			swap_ipv4(h.ipv4);
+			next_proto = h.ipv4->next_proto_id;
+			mb->l3_len = rte_ipv4_hdr_len(h.ipv4);
+			h.byte += mb->l3_len;
+		} else if (proto == RTE_BE16(RTE_ETHER_TYPE_IPV6)) {
+			swap_ipv6(h.ipv6);
+			next_proto = h.ipv6->proto;
+			h.ipv6++;
+			mb->l3_len = sizeof(struct rte_ipv6_hdr);
+		} else {
+			mbuf_field_set(mb, ol_flags);
+			continue;
+		}
+		if (next_proto == IPPROTO_UDP) {
+			swap_udp(h.udp);
+			mb->l4_len = sizeof(struct rte_udp_hdr);
+		} else if (next_proto == IPPROTO_TCP) {
+			swap_tcp(h.tcp);
+			mb->l4_len = (h.tcp->data_off & 0xf0) >> 2;
+		}
+		mbuf_field_set(mb, ol_flags);
+	}
+}
+
+#endif /* _5TSWAP_H_ */
diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c
index 096c218c12..d55212bbad 100644
--- a/app/test-pmd/config.c
+++ b/app/test-pmd/config.c
@@ -4052,9 +4052,16 @@ rxtx_config_display(void)
 {
 	portid_t pid;
 	queueid_t qid;
+	char buf[32];
+
+	if (cur_fwd_eng->status)
+		snprintf(buf, sizeof(buf), " (%s)", cur_fwd_eng->status);
+	else
+		buf[0] = '\0';
 
-	printf("  %s packet forwarding%s packets/burst=%d\n",
+	printf("  %s%s packet forwarding%s packets/burst=%d\n",
 	       cur_fwd_eng->fwd_mode_name,
+	       buf,
 	       retry_enabled == 0 ? "" : " with retry",
 	       nb_pkt_per_burst);
 
@@ -4816,10 +4823,17 @@ pkt_fwd_config_display(struct fwd_config *cfg)
 	struct fwd_stream *fs;
 	lcoreid_t  lc_id;
 	streamid_t sm_id;
+	char buf[32];
+
+	if (cfg->fwd_eng->status)
+		snprintf(buf, sizeof(buf), " (%s)", cfg->fwd_eng->status);
+	else
+		buf[0] = '\0';
 
-	printf("%s packet forwarding%s - ports=%d - cores=%d - streams=%d - "
+	printf("%s%s packet forwarding%s - ports=%d - cores=%d - streams=%d - "
 		"NUMA support %s, MP allocation mode: %s\n",
 		cfg->fwd_eng->fwd_mode_name,
+		buf,
 		retry_enabled == 0 ? "" : " with retry",
 		cfg->nb_fwd_ports, cfg->nb_fwd_lcores, cfg->nb_fwd_streams,
 		numa_support == 1 ? "enabled" : "disabled",
diff --git a/app/test-pmd/macfwd.c b/app/test-pmd/macfwd.c
index 7316d73315..d19ace7395 100644
--- a/app/test-pmd/macfwd.c
+++ b/app/test-pmd/macfwd.c
@@ -35,6 +35,7 @@
 #include <rte_flow.h>
 
 #include "testpmd.h"
+#include "macfwd.h"
 
 /*
  * Forwarding of packets in MAC mode.
@@ -45,13 +46,7 @@ static bool
 pkt_burst_mac_forward(struct fwd_stream *fs)
 {
 	struct rte_mbuf  *pkts_burst[MAX_PKT_BURST];
-	struct rte_port  *txp;
-	struct rte_mbuf  *mb;
-	struct rte_ether_hdr *eth_hdr;
 	uint16_t nb_rx;
-	uint16_t i;
-	uint64_t ol_flags = 0;
-	uint64_t tx_offloads;
 
 	/*
 	 * Receive a burst of packets and forward them.
@@ -60,31 +55,7 @@ pkt_burst_mac_forward(struct fwd_stream *fs)
 	if (unlikely(nb_rx == 0))
 		return false;
 
-	txp = &ports[fs->tx_port];
-	tx_offloads = txp->dev_conf.txmode.offloads;
-	if (tx_offloads	& RTE_ETH_TX_OFFLOAD_VLAN_INSERT)
-		ol_flags = RTE_MBUF_F_TX_VLAN;
-	if (tx_offloads & RTE_ETH_TX_OFFLOAD_QINQ_INSERT)
-		ol_flags |= RTE_MBUF_F_TX_QINQ;
-	if (tx_offloads & RTE_ETH_TX_OFFLOAD_MACSEC_INSERT)
-		ol_flags |= RTE_MBUF_F_TX_MACSEC;
-	for (i = 0; i < nb_rx; i++) {
-		if (likely(i < nb_rx - 1))
-			rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i + 1],
-						       void *));
-		mb = pkts_burst[i];
-		eth_hdr = rte_pktmbuf_mtod(mb, struct rte_ether_hdr *);
-		rte_ether_addr_copy(&peer_eth_addrs[fs->peer_addr],
-				&eth_hdr->dst_addr);
-		rte_ether_addr_copy(&ports[fs->tx_port].eth_addr,
-				&eth_hdr->src_addr);
-		mb->ol_flags &= RTE_MBUF_F_INDIRECT | RTE_MBUF_F_EXTERNAL;
-		mb->ol_flags |= ol_flags;
-		mb->l2_len = sizeof(struct rte_ether_hdr);
-		mb->l3_len = sizeof(struct rte_ipv4_hdr);
-		mb->vlan_tci = txp->tx_vlan_id;
-		mb->vlan_tci_outer = txp->tx_vlan_id_outer;
-	}
+	do_macfwd(pkts_burst, nb_rx, fs);
 
 	common_fwd_stream_transmit(fs, pkts_burst, nb_rx);
 
diff --git a/app/test-pmd/macfwd.h b/app/test-pmd/macfwd.h
new file mode 100644
index 0000000000..ae2346e589
--- /dev/null
+++ b/app/test-pmd/macfwd.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2014 Intel Corporation
+ */
+
+#ifndef _MACFWD_H_
+#define _MACFWD_H_
+
+static inline void
+do_macfwd(struct rte_mbuf *pkts_burst[], uint16_t nb_rx,
+	  struct fwd_stream *fs)
+{
+	struct rte_ether_hdr *eth_hdr;
+	uint64_t ol_flags = 0;
+	uint64_t tx_offloads;
+	struct rte_mbuf  *mb;
+	struct rte_port *txp = &ports[fs->tx_port];
+	uint16_t i;
+
+	tx_offloads = txp->dev_conf.txmode.offloads;
+	if (tx_offloads	& RTE_ETH_TX_OFFLOAD_VLAN_INSERT)
+		ol_flags = RTE_MBUF_F_TX_VLAN;
+	if (tx_offloads & RTE_ETH_TX_OFFLOAD_QINQ_INSERT)
+		ol_flags |= RTE_MBUF_F_TX_QINQ;
+	if (tx_offloads & RTE_ETH_TX_OFFLOAD_MACSEC_INSERT)
+		ol_flags |= RTE_MBUF_F_TX_MACSEC;
+	for (i = 0; i < nb_rx; i++) {
+		if (likely(i < nb_rx - 1))
+			rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i + 1],
+						       void *));
+		mb = pkts_burst[i];
+		eth_hdr = rte_pktmbuf_mtod(mb, struct rte_ether_hdr *);
+		rte_ether_addr_copy(&peer_eth_addrs[fs->peer_addr],
+				    &eth_hdr->dst_addr);
+		rte_ether_addr_copy(&ports[fs->tx_port].eth_addr,
+				    &eth_hdr->src_addr);
+		mb->ol_flags &= RTE_MBUF_F_INDIRECT | RTE_MBUF_F_EXTERNAL;
+		mb->ol_flags |= ol_flags;
+		mb->l2_len = sizeof(struct rte_ether_hdr);
+		mb->l3_len = sizeof(struct rte_ipv4_hdr);
+		mb->vlan_tci = txp->tx_vlan_id;
+		mb->vlan_tci_outer = txp->tx_vlan_id_outer;
+	}
+}
+
+#endif /* _MACFWD_H_ */
diff --git a/app/test-pmd/noisy_vnf.c b/app/test-pmd/noisy_vnf.c
index 2bf90a983c..81d1187cfe 100644
--- a/app/test-pmd/noisy_vnf.c
+++ b/app/test-pmd/noisy_vnf.c
@@ -32,6 +32,18 @@
 #include <rte_malloc.h>
 
 #include "testpmd.h"
+#include "5tswap.h"
+#include "macfwd.h"
+#if defined(RTE_ARCH_X86)
+#include "macswap_sse.h"
+#elif defined(__ARM_NEON)
+#include "macswap_neon.h"
+#else
+#include "macswap.h"
+#endif
+
+#define NOISY_STRSIZE 256
+#define NOISY_RING "noisy_ring_%d\n"
 
 struct noisy_config {
 	struct rte_ring *f;
@@ -80,9 +92,6 @@ sim_memory_lookups(struct noisy_config *ncf, uint16_t nb_pkts)
 {
 	uint16_t i, j;
 
-	if (!ncf->do_sim)
-		return;
-
 	for (i = 0; i < nb_pkts; i++) {
 		for (j = 0; j < noisy_lkup_num_writes; j++)
 			do_write(ncf->vnf_mem);
@@ -110,15 +119,13 @@ sim_memory_lookups(struct noisy_config *ncf, uint16_t nb_pkts)
  *    out of the FIFO
  * 4. Cases 2 and 3 combined
  */
-static bool
-pkt_burst_noisy_vnf(struct fwd_stream *fs)
+static uint16_t
+noisy_eth_tx_burst(struct fwd_stream *fs, uint16_t nb_rx, struct rte_mbuf **pkts_burst)
 {
 	const uint64_t freq_khz = rte_get_timer_hz() / 1000;
 	struct noisy_config *ncf = noisy_cfg[fs->rx_port];
-	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
 	struct rte_mbuf *tmp_pkts[MAX_PKT_BURST];
 	uint16_t nb_deqd = 0;
-	uint16_t nb_rx = 0;
 	uint16_t nb_tx = 0;
 	uint16_t nb_enqd;
 	unsigned int fifo_free;
@@ -126,12 +133,16 @@ pkt_burst_noisy_vnf(struct fwd_stream *fs)
 	bool needs_flush = false;
 	uint64_t now;
 
-	nb_rx = common_fwd_stream_receive(fs, pkts_burst, nb_pkt_per_burst);
-	if (unlikely(nb_rx == 0))
-		goto flush;
+	if (unlikely(nb_rx == 0)) {
+		if (!ncf->do_buffering)
+			goto end;
+		else
+			goto flush;
+	}
 
 	if (!ncf->do_buffering) {
-		sim_memory_lookups(ncf, nb_rx);
+		if (ncf->do_sim)
+			sim_memory_lookups(ncf, nb_rx);
 		nb_tx = common_fwd_stream_transmit(fs, pkts_burst, nb_rx);
 		goto end;
 	}
@@ -150,7 +161,8 @@ pkt_burst_noisy_vnf(struct fwd_stream *fs)
 			nb_tx = common_fwd_stream_transmit(fs, tmp_pkts, nb_deqd);
 	}
 
-	sim_memory_lookups(ncf, nb_enqd);
+	if (ncf->do_sim)
+		sim_memory_lookups(ncf, nb_enqd);
 
 flush:
 	if (ncf->do_flush) {
@@ -169,11 +181,66 @@ pkt_burst_noisy_vnf(struct fwd_stream *fs)
 		ncf->prev_time = rte_get_timer_cycles();
 	}
 end:
+	return nb_tx;
+}
+
+static bool
+pkt_burst_io(struct fwd_stream *fs)
+{
+	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
+	uint16_t nb_rx;
+	uint16_t nb_tx;
+
+	nb_rx = common_fwd_stream_receive(fs, pkts_burst, nb_pkt_per_burst);
+	nb_tx = noisy_eth_tx_burst(fs, nb_rx, pkts_burst);
+
 	return nb_rx > 0 || nb_tx > 0;
 }
 
-#define NOISY_STRSIZE 256
-#define NOISY_RING "noisy_ring_%d\n"
+static bool
+pkt_burst_mac(struct fwd_stream *fs)
+{
+	struct rte_mbuf  *pkts_burst[MAX_PKT_BURST];
+	uint16_t nb_rx;
+	uint16_t nb_tx;
+
+	nb_rx = common_fwd_stream_receive(fs, pkts_burst, nb_pkt_per_burst);
+	if (likely(nb_rx != 0))
+		do_macfwd(pkts_burst, nb_rx, fs);
+	nb_tx = noisy_eth_tx_burst(fs, nb_rx, pkts_burst);
+
+	return nb_rx > 0 || nb_tx > 0;
+}
+
+static bool
+pkt_burst_macswap(struct fwd_stream *fs)
+{
+	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
+	uint16_t nb_rx;
+	uint16_t nb_tx;
+
+	nb_rx = common_fwd_stream_receive(fs, pkts_burst, nb_pkt_per_burst);
+	if (likely(nb_rx != 0))
+		do_macswap(pkts_burst, nb_rx, &ports[fs->tx_port]);
+	nb_tx = noisy_eth_tx_burst(fs, nb_rx, pkts_burst);
+
+	return nb_rx > 0 || nb_tx > 0;
+}
+
+static bool
+pkt_burst_5tswap(struct fwd_stream *fs)
+{
+	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
+	uint16_t nb_rx;
+	uint16_t nb_tx;
+
+	nb_rx = common_fwd_stream_receive(fs, pkts_burst, nb_pkt_per_burst);
+	if (likely(nb_rx != 0))
+		do_5tswap(pkts_burst, nb_rx, fs);
+	nb_tx = noisy_eth_tx_burst(fs, nb_rx, pkts_burst);
+
+	return nb_rx > 0 || nb_tx > 0;
+}
 
 static void
 noisy_fwd_end(portid_t pi)
@@ -226,6 +293,20 @@ noisy_fwd_begin(portid_t pi)
 			 "--noisy-lkup-memory-size must be > 0\n");
 	}
 
+	if (noisy_fwd_mode == NOISY_FWD_MODE_IO)
+		noisy_vnf_engine.packet_fwd = pkt_burst_io;
+	else if (noisy_fwd_mode == NOISY_FWD_MODE_MAC)
+		noisy_vnf_engine.packet_fwd = pkt_burst_mac;
+	else if (noisy_fwd_mode == NOISY_FWD_MODE_MACSWAP)
+		noisy_vnf_engine.packet_fwd = pkt_burst_macswap;
+	else if (noisy_fwd_mode == NOISY_FWD_MODE_5TSWAP)
+		noisy_vnf_engine.packet_fwd = pkt_burst_5tswap;
+	else
+		rte_exit(EXIT_FAILURE,
+			 " Invalid noisy_fwd_mode specified\n");
+
+	noisy_vnf_engine.status = noisy_fwd_mode_desc[noisy_fwd_mode];
+
 	return 0;
 }
 
@@ -233,6 +314,6 @@ struct fwd_engine noisy_vnf_engine = {
 	.fwd_mode_name  = "noisy",
 	.port_fwd_begin = noisy_fwd_begin,
 	.port_fwd_end   = noisy_fwd_end,
-	.stream_init    = common_fwd_stream_init,
-	.packet_fwd     = pkt_burst_noisy_vnf,
+	.stream_init	= common_fwd_stream_init,
+	.packet_fwd     = pkt_burst_io,
 };
diff --git a/app/test-pmd/parameters.c b/app/test-pmd/parameters.c
index 3b37809baf..b676f2c6ae 100644
--- a/app/test-pmd/parameters.c
+++ b/app/test-pmd/parameters.c
@@ -190,6 +190,7 @@ usage(char* progname)
 	       "    anon: use regular DPDK memory to create and anonymous memory to populate mempool\n"
 	       "    xmem: use anonymous memory to create and populate mempool\n"
 	       "    xmemhuge: use anonymous hugepage memory to create and populate mempool\n");
+	printf("  --noisy-forward-mode=<io|mac|macswap|5tswap>: set the sub-fwd mode, defaults to io\n");
 	printf("  --noisy-tx-sw-buffer-size=N: size of FIFO buffer\n");
 	printf("  --noisy-tx-sw-buffer-flushtime=N: flush FIFO after N ms\n");
 	printf("  --noisy-lkup-memory=N: allocate N MB of VNF memory\n");
@@ -698,6 +699,7 @@ launch_args_parse(int argc, char** argv)
 		{ "mp-alloc",			1, 0, 0 },
 		{ "tx-ip",			1, 0, 0 },
 		{ "tx-udp",			1, 0, 0 },
+		{ "noisy-forward-mode",		1, 0, 0 },
 		{ "noisy-tx-sw-buffer-size",	1, 0, 0 },
 		{ "noisy-tx-sw-buffer-flushtime", 1, 0, 0 },
 		{ "noisy-lkup-memory",		1, 0, 0 },
@@ -1444,6 +1446,19 @@ launch_args_parse(int argc, char** argv)
 					rte_exit(EXIT_FAILURE,
 						 "noisy-lkup-num-reads-writes must be >= 0\n");
 			}
+			if (!strcmp(lgopts[opt_idx].name,
+				    "noisy-forward-mode")) {
+				int i;
+				for (i = 0; i < NOISY_FWD_MODE_MAX; i++)
+					if (!strcmp(optarg, noisy_fwd_mode_desc[i])) {
+						noisy_fwd_mode = i;
+						break;
+					}
+				if (i == NOISY_FWD_MODE_MAX)
+					rte_exit(EXIT_FAILURE, "noisy-forward-mode %s invalid,"
+						 " must be a valid noisy-forward-mode value\n",
+						 optarg);
+			}
 			if (!strcmp(lgopts[opt_idx].name, "no-iova-contig"))
 				mempool_flags = RTE_MEMPOOL_F_NO_IOVA_CONTIG;
 
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index 5cb6f92523..c6ad9b18bf 100644
--- a/app/test-pmd/testpmd.c
+++ b/app/test-pmd/testpmd.c
@@ -330,6 +330,20 @@ int16_t tx_free_thresh = RTE_PMD_PARAM_UNSET;
  */
 int16_t tx_rs_thresh = RTE_PMD_PARAM_UNSET;
 
+/*
+ * Configurable sub-forwarding mode for the noisy_vnf forwarding mode.
+ */
+enum noisy_fwd_mode noisy_fwd_mode;
+
+/* String version of enum noisy_fwd_mode */
+const char * const noisy_fwd_mode_desc[] = {
+	[NOISY_FWD_MODE_IO] = "io",
+	[NOISY_FWD_MODE_MAC] = "mac",
+	[NOISY_FWD_MODE_MACSWAP] = "macswap",
+	[NOISY_FWD_MODE_5TSWAP] = "5tswap",
+	[NOISY_FWD_MODE_MAX] = NULL,
+};
+
 /*
  * Configurable value of buffered packets before sending.
  */
diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h
index bdfbfd36d3..2f18cf20a2 100644
--- a/app/test-pmd/testpmd.h
+++ b/app/test-pmd/testpmd.h
@@ -116,6 +116,14 @@ enum {
 	QUEUE_JOB_TYPE_ACTION_QUERY,
 };
 
+enum noisy_fwd_mode {
+	NOISY_FWD_MODE_IO,
+	NOISY_FWD_MODE_MAC,
+	NOISY_FWD_MODE_MACSWAP,
+	NOISY_FWD_MODE_5TSWAP,
+	NOISY_FWD_MODE_MAX,
+};
+
 /**
  * The data structure associated with RX and TX packet burst statistics
  * that are recorded for each forwarding stream.
@@ -391,6 +399,7 @@ struct fwd_engine {
 	port_fwd_end_t   port_fwd_end;   /**< NULL if nothing special to do. */
 	stream_init_t    stream_init;    /**< NULL if nothing special to do. */
 	packet_fwd_t     packet_fwd;     /**< Mandatory. */
+	const char       *status;        /**< NULL if nothing to display. */
 };
 
 void common_fwd_stream_init(struct fwd_stream *fs);
@@ -555,6 +564,8 @@ extern int8_t rx_drop_en;
 extern int16_t tx_free_thresh;
 extern int16_t tx_rs_thresh;
 
+extern enum noisy_fwd_mode noisy_fwd_mode;
+extern const char * const noisy_fwd_mode_desc[];
 extern uint16_t noisy_tx_sw_bufsz;
 extern uint16_t noisy_tx_sw_buf_flush_time;
 extern uint64_t noisy_lkup_mem_sz;
diff --git a/doc/guides/testpmd_app_ug/run_app.rst b/doc/guides/testpmd_app_ug/run_app.rst
index 57b23241cf..8319a30968 100644
--- a/doc/guides/testpmd_app_ug/run_app.rst
+++ b/doc/guides/testpmd_app_ug/run_app.rst
@@ -487,6 +487,15 @@ The command line options are:
     * xmemhuge: create and populate mempool using externally and anonymously
       allocated hugepage area
 
+*   ``--noisy-forward-mode=mode``
+
+    Set the noisy vnf forwarding mode where ``mode`` is one of the following::
+
+       io (the default)
+       mac
+       macswap
+       5tswap
+
 *   ``--noisy-tx-sw-buffer-size``
 
     Set the number of maximum elements  of the FIFO queue to be created
-- 
2.31.1