[dpdk-dev] [RFC PATCH 13/14] mbuf: cleanup + added in additional mbuf fields.

[Bruce Richardson <bruce.richardson@intel.com>]

Cleanups:
* use typedefs for markers within mbuf struct
* split up vlan_macip field as the l2/l3 lengths are for TX so go on the
  second cache line.
* created a tx_ol field in second cache line for data used for tx
  offloads
* rename the hash field to the filter field as it contains more than
  just a hash value.

Added in the extra mbuf fields needed:
* fdir flex bytes for i40e driver, i.e. extra 32-bits for filters
* field to be used for a sequence number, extra 32-bit field
* field for a second vlan tag, extra 16-bits, using space freed by
  moving out the l2 l3 lengths.
* userdata field for general application use.
* added inner_l3 and l4 length fields to allow tunneling.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
---
 app/test-pmd/csumonly.c                     |  4 +-
 app/test-pmd/flowgen.c                      |  6 +-
 app/test-pmd/macfwd.c                       |  6 +-
 app/test-pmd/macswap.c                      |  6 +-
 app/test-pmd/rxonly.c                       |  7 +--
 app/test-pmd/testpmd.c                      |  5 +-
 app/test-pmd/txonly.c                       |  6 +-
 app/test/packet_burst_generator.c           | 10 ++--
 app/test/test_distributor.c                 | 18 +++---
 app/test/test_distributor_perf.c            |  4 +-
 lib/librte_distributor/rte_distributor.c    |  2 +-
 lib/librte_ip_frag/ip_frag_common.h         |  3 +-
 lib/librte_ip_frag/rte_ipv4_fragmentation.c |  2 +-
 lib/librte_ip_frag/rte_ipv4_reassembly.c    |  6 +-
 lib/librte_ip_frag/rte_ipv6_reassembly.c    |  5 +-
 lib/librte_mbuf/rte_mbuf.h                  | 88 ++++++++++++++++-------------
 lib/librte_pmd_e1000/e1000_ethdev.h         | 21 +++++++
 lib/librte_pmd_e1000/em_rxtx.c              | 13 +++--
 lib/librte_pmd_e1000/igb_rxtx.c             | 20 +++----
 lib/librte_pmd_i40e/i40e_rxtx.c             | 22 ++++----
 lib/librte_pmd_ixgbe/ixgbe_ethdev.h         | 21 +++++++
 lib/librte_pmd_ixgbe/ixgbe_rxtx.c           | 28 ++++-----
 lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c       |  8 +--
 lib/librte_pmd_vmxnet3/vmxnet3_rxtx.c       |  4 +-
 lib/librte_sched/rte_sched.h                | 19 ++++---
 25 files changed, 198 insertions(+), 136 deletions(-)

diff --git a/app/test-pmd/csumonly.c b/app/test-pmd/csumonly.c
index 6a3aaf0..e7bf794 100644
--- a/app/test-pmd/csumonly.c
+++ b/app/test-pmd/csumonly.c
@@ -432,8 +432,8 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
 		}
 
 		/* Combine the packet header write. VLAN is not consider here */
-		mb->vlan_macip.f.l2_len = l2_len;
-		mb->vlan_macip.f.l3_len = l3_len;
+		mb->tx_ol.l2_len = l2_len;
+		mb->tx_ol.l3_len = l3_len;
 		mb->ol_flags = ol_flags;
 	}
 	nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, pkts_burst, nb_rx);
diff --git a/app/test-pmd/flowgen.c b/app/test-pmd/flowgen.c
index d69b2b8..a4e758a 100644
--- a/app/test-pmd/flowgen.c
+++ b/app/test-pmd/flowgen.c
@@ -208,9 +208,9 @@ pkt_burst_flow_gen(struct fwd_stream *fs)
 		pkt->nb_segs			= 1;
 		pkt->pkt_len			= pkt_size;
 		pkt->ol_flags			= ol_flags;
-		pkt->vlan_macip.f.vlan_tci	= vlan_tci;
-		pkt->vlan_macip.f.l2_len	= sizeof(struct ether_hdr);
-		pkt->vlan_macip.f.l3_len	= sizeof(struct ipv4_hdr);
+		pkt->vlan_tci0			= vlan_tci;
+		pkt->tx_ol.l2_len		= sizeof(struct ether_hdr);
+		pkt->tx_ol.l3_len		= sizeof(struct ipv4_hdr);
 		pkts_burst[nb_pkt]		= pkt;
 
 		next_flow = (next_flow + 1) % cfg_n_flows;
diff --git a/app/test-pmd/macfwd.c b/app/test-pmd/macfwd.c
index 674c189..c0791dd 100644
--- a/app/test-pmd/macfwd.c
+++ b/app/test-pmd/macfwd.c
@@ -116,9 +116,9 @@ pkt_burst_mac_forward(struct fwd_stream *fs)
 		ether_addr_copy(&ports[fs->tx_port].eth_addr,
 				&eth_hdr->s_addr);
 		mb->ol_flags = txp->tx_ol_flags;
-		mb->vlan_macip.f.l2_len = sizeof(struct ether_hdr);
-		mb->vlan_macip.f.l3_len = sizeof(struct ipv4_hdr);
-		mb->vlan_macip.f.vlan_tci = txp->tx_vlan_id;
+		mb->tx_ol.l2_len = sizeof(struct ether_hdr);
+		mb->tx_ol.l3_len = sizeof(struct ipv4_hdr);
+		mb->vlan_tci0 = txp->tx_vlan_id;
 	}
 	nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, pkts_burst, nb_rx);
 	fs->tx_packets += nb_tx;
diff --git a/app/test-pmd/macswap.c b/app/test-pmd/macswap.c
index d274b36..517bb73 100644
--- a/app/test-pmd/macswap.c
+++ b/app/test-pmd/macswap.c
@@ -118,9 +118,9 @@ pkt_burst_mac_swap(struct fwd_stream *fs)
 		ether_addr_copy(&addr, &eth_hdr->s_addr);
 
 		mb->ol_flags = txp->tx_ol_flags;
-		mb->vlan_macip.f.l2_len = sizeof(struct ether_hdr);
-		mb->vlan_macip.f.l3_len = sizeof(struct ipv4_hdr);
-		mb->vlan_macip.f.vlan_tci = txp->tx_vlan_id;
+		mb->tx_ol.l2_len = sizeof(struct ether_hdr);
+		mb->tx_ol.l3_len = sizeof(struct ipv4_hdr);
+		mb->vlan_tci0 = txp->tx_vlan_id;
 	}
 	nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, pkts_burst, nb_rx);
 	fs->tx_packets += nb_tx;
diff --git a/app/test-pmd/rxonly.c b/app/test-pmd/rxonly.c
index b477076..95a77a4 100644
--- a/app/test-pmd/rxonly.c
+++ b/app/test-pmd/rxonly.c
@@ -158,15 +158,14 @@ pkt_burst_receive(struct fwd_stream *fs)
 		       eth_type, (unsigned) mb->pkt_len,
 		       (int)mb->nb_segs);
 		if (ol_flags & PKT_RX_RSS_HASH) {
-			printf(" - RSS hash=0x%x", (unsigned) mb->hash.rss);
+			printf(" - RSS hash=0x%x", (unsigned) mb->filters.rss);
 			printf(" - RSS queue=0x%x",(unsigned) fs->rx_queue);
 		}
 		else if (ol_flags & PKT_RX_FDIR)
 			printf(" - FDIR hash=0x%x - FDIR id=0x%x ",
-			       mb->hash.fdir.hash, mb->hash.fdir.id);
+			       mb->filters.fdir.hash, mb->filters.fdir.id);
 		if (ol_flags & PKT_RX_VLAN_PKT)
-			printf(" - VLAN tci=0x%x",
-				mb->vlan_macip.f.vlan_tci);
+			printf(" - VLAN tci=0x%x", mb->vlan_tci0);
 		printf("\n");
 		if (ol_flags != 0) {
 			int rxf;
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index 16de06c..532d139 100644
--- a/app/test-pmd/testpmd.c
+++ b/app/test-pmd/testpmd.c
@@ -406,8 +406,9 @@ testpmd_mbuf_ctor(struct rte_mempool *mp,
 	mb->ol_flags     = 0;
 	mb->data_off     = RTE_PKTMBUF_HEADROOM;
 	mb->nb_segs      = 1;
-	mb->vlan_macip.data = 0;
-	mb->hash.rss     = 0;
+	mb->vlan_tci0    = 0;
+	mb->tx_ol.u64    = 0;
+	mb->filters.rss  = 0;
 }
 
 static void
diff --git a/app/test-pmd/txonly.c b/app/test-pmd/txonly.c
index 95e46a2..57d6c60 100644
--- a/app/test-pmd/txonly.c
+++ b/app/test-pmd/txonly.c
@@ -264,9 +264,9 @@ pkt_burst_transmit(struct fwd_stream *fs)
 		pkt->nb_segs = tx_pkt_nb_segs;
 		pkt->pkt_len = tx_pkt_length;
 		pkt->ol_flags = ol_flags;
-		pkt->vlan_macip.f.vlan_tci  = vlan_tci;
-		pkt->vlan_macip.f.l2_len = sizeof(struct ether_hdr);
-		pkt->vlan_macip.f.l3_len = sizeof(struct ipv4_hdr);
+		pkt->vlan_tci0  = vlan_tci;
+		pkt->tx_ol.l2_len = sizeof(struct ether_hdr);
+		pkt->tx_ol.l3_len = sizeof(struct ipv4_hdr);
 		pkts_burst[nb_pkt] = pkt;
 	}
 	nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, pkts_burst, nb_pkt);
diff --git a/app/test/packet_burst_generator.c b/app/test/packet_burst_generator.c
index c9e6c8b..bb14f83 100644
--- a/app/test/packet_burst_generator.c
+++ b/app/test/packet_burst_generator.c
@@ -261,19 +261,19 @@ nomore_mbuf:
 		 */
 		pkt->nb_segs = tx_pkt_nb_segs;
 		pkt->pkt_len = tx_pkt_length;
-		pkt->vlan_macip.f.l2_len = eth_hdr_size;
+		pkt->tx_ol.l2_len = eth_hdr_size;
 
 		if (ipv4) {
-			pkt->vlan_macip.f.vlan_tci  = ETHER_TYPE_IPv4;
-			pkt->vlan_macip.f.l3_len = sizeof(struct ipv4_hdr);
+			pkt->vlan_tci0  = ETHER_TYPE_IPv4;
+			pkt->tx_ol.l3_len = sizeof(struct ipv4_hdr);
 
 			if (vlan_enabled)
 				pkt->ol_flags = PKT_RX_IPV4_HDR | PKT_RX_VLAN_PKT;
 			else
 				pkt->ol_flags = PKT_RX_IPV4_HDR;
 		} else {
-			pkt->vlan_macip.f.vlan_tci  = ETHER_TYPE_IPv6;
-			pkt->vlan_macip.f.l3_len = sizeof(struct ipv6_hdr);
+			pkt->vlan_tci0  = ETHER_TYPE_IPv6;
+			pkt->tx_ol.l3_len = sizeof(struct ipv6_hdr);
 
 			if (vlan_enabled)
 				pkt->ol_flags = PKT_RX_IPV6_HDR | PKT_RX_VLAN_PKT;
diff --git a/app/test/test_distributor.c b/app/test/test_distributor.c
index 0e96d42..3d922e9 100644
--- a/app/test/test_distributor.c
+++ b/app/test/test_distributor.c
@@ -121,7 +121,7 @@ sanity_test(struct rte_distributor *d, struct rte_mempool *p)
 	/* now set all hash values in all buffers to zero, so all pkts go to the
 	 * one worker thread */
 	for (i = 0; i < BURST; i++)
-		bufs[i]->hash.rss = 0;
+		bufs[i]->filters.rss = 0;
 
 	rte_distributor_process(d, bufs, BURST);
 	rte_distributor_flush(d);
@@ -143,7 +143,7 @@ sanity_test(struct rte_distributor *d, struct rte_mempool *p)
 	if (rte_lcore_count() >= 3) {
 		clear_packet_count();
 		for (i = 0; i < BURST; i++)
-			bufs[i]->hash.rss = (i & 1) << 8;
+			bufs[i]->filters.rss = (i & 1) << 8;
 
 		rte_distributor_process(d, bufs, BURST);
 		rte_distributor_flush(d);
@@ -168,7 +168,7 @@ sanity_test(struct rte_distributor *d, struct rte_mempool *p)
 	 * so load gets distributed */
 	clear_packet_count();
 	for (i = 0; i < BURST; i++)
-		bufs[i]->hash.rss = i;
+		bufs[i]->filters.rss = i;
 
 	rte_distributor_process(d, bufs, BURST);
 	rte_distributor_flush(d);
@@ -200,7 +200,7 @@ sanity_test(struct rte_distributor *d, struct rte_mempool *p)
 		return -1;
 	}
 	for (i = 0; i < BIG_BATCH; i++)
-		many_bufs[i]->hash.rss = i << 2;
+		many_bufs[i]->filters.rss = i << 2;
 
 	for (i = 0; i < BIG_BATCH/BURST; i++) {
 		rte_distributor_process(d, &many_bufs[i*BURST], BURST);
@@ -281,7 +281,7 @@ sanity_test_with_mbuf_alloc(struct rte_distributor *d, struct rte_mempool *p)
 		while (rte_mempool_get_bulk(p, (void *)bufs, BURST) < 0)
 			rte_distributor_process(d, NULL, 0);
 		for (j = 0; j < BURST; j++) {
-			bufs[j]->hash.rss = (i+j) << 1;
+			bufs[j]->filters.rss = (i+j) << 1;
 			bufs[j]->refcnt = 1;
 		}
 
@@ -360,7 +360,7 @@ sanity_test_with_worker_shutdown(struct rte_distributor *d,
 	/* now set all hash values in all buffers to zero, so all pkts go to the
 	 * one worker thread */
 	for (i = 0; i < BURST; i++)
-		bufs[i]->hash.rss = 0;
+		bufs[i]->filters.rss = 0;
 
 	rte_distributor_process(d, bufs, BURST);
 	/* at this point, we will have processed some packets and have a full
@@ -373,7 +373,7 @@ sanity_test_with_worker_shutdown(struct rte_distributor *d,
 		return -1;
 	}
 	for (i = 0; i < BURST; i++)
-		bufs[i]->hash.rss = 0;
+		bufs[i]->filters.rss = 0;
 
 	/* get worker zero to quit */
 	zero_quit = 1;
@@ -417,7 +417,7 @@ test_flush_with_worker_shutdown(struct rte_distributor *d,
 	/* now set all hash values in all buffers to zero, so all pkts go to the
 	 * one worker thread */
 	for (i = 0; i < BURST; i++)
-		bufs[i]->hash.rss = 0;
+		bufs[i]->filters.rss = 0;
 
 	rte_distributor_process(d, bufs, BURST);
 	/* at this point, we will have processed some packets and have a full
@@ -489,7 +489,7 @@ quit_workers(struct rte_distributor *d, struct rte_mempool *p)
 	zero_quit = 0;
 	quit = 1;
 	for (i = 0; i < num_workers; i++)
-		bufs[i]->hash.rss = i << 1;
+		bufs[i]->filters.rss = i << 1;
 	rte_distributor_process(d, bufs, num_workers);
 
 	rte_mempool_put_bulk(p, (void *)bufs, num_workers);
diff --git a/app/test/test_distributor_perf.c b/app/test/test_distributor_perf.c
index 7ecbc6b..f9e0d57 100644
--- a/app/test/test_distributor_perf.c
+++ b/app/test/test_distributor_perf.c
@@ -160,7 +160,7 @@ perf_test(struct rte_distributor *d, struct rte_mempool *p)
 	}
 	/* ensure we have different hash value for each pkt */
 	for (i = 0; i < BURST; i++)
-		bufs[i]->hash.rss = i;
+		bufs[i]->filters.rss = i;
 
 	start = rte_rdtsc();
 	for (i = 0; i < (1<<ITER_POWER); i++)
@@ -199,7 +199,7 @@ quit_workers(struct rte_distributor *d, struct rte_mempool *p)
 
 	quit = 1;
 	for (i = 0; i < num_workers; i++)
-		bufs[i]->hash.rss = i << 1;
+		bufs[i]->filters.rss = i << 1;
 	rte_distributor_process(d, bufs, num_workers);
 
 	rte_mempool_put_bulk(p, (void *)bufs, num_workers);
diff --git a/lib/librte_distributor/rte_distributor.c b/lib/librte_distributor/rte_distributor.c
index 585ff88..7aed7f1 100644
--- a/lib/librte_distributor/rte_distributor.c
+++ b/lib/librte_distributor/rte_distributor.c
@@ -282,7 +282,7 @@ rte_distributor_process(struct rte_distributor *d,
 			next_mb = mbufs[next_idx++];
 			next_value = (((int64_t)(uintptr_t)next_mb)
 					<< RTE_DISTRIB_FLAG_BITS);
-			new_tag = (next_mb->hash.rss | 1);
+			new_tag = (next_mb->filters.rss | 1);
 
 			uint32_t match = 0;
 			unsigned i;
diff --git a/lib/librte_ip_frag/ip_frag_common.h b/lib/librte_ip_frag/ip_frag_common.h
index 81ca23a..0a48dec 100644
--- a/lib/librte_ip_frag/ip_frag_common.h
+++ b/lib/librte_ip_frag/ip_frag_common.h
@@ -173,8 +173,7 @@ ip_frag_chain(struct rte_mbuf *mn, struct rte_mbuf *mp)
 	struct rte_mbuf *ms;
 
 	/* adjust start of the last fragment data. */
-	rte_pktmbuf_adj(mp, (uint16_t)(mp->vlan_macip.f.l2_len +
-		mp->vlan_macip.f.l3_len));
+	rte_pktmbuf_adj(mp, (uint16_t)(mp->tx_ol.l2_len + mp->tx_ol.l3_len));
 
 	/* chain two fragments. */
 	ms = rte_pktmbuf_lastseg(mn);
diff --git a/lib/librte_ip_frag/rte_ipv4_fragmentation.c b/lib/librte_ip_frag/rte_ipv4_fragmentation.c
index cb09d92..5165b25 100644
--- a/lib/librte_ip_frag/rte_ipv4_fragmentation.c
+++ b/lib/librte_ip_frag/rte_ipv4_fragmentation.c
@@ -198,7 +198,7 @@ rte_ipv4_fragment_packet(struct rte_mbuf *pkt_in,
 		    out_pkt->pkt_len - sizeof(struct ipv4_hdr));
 
 		out_pkt->ol_flags |= PKT_TX_IP_CKSUM;
-		out_pkt->vlan_macip.f.l3_len = sizeof(struct ipv4_hdr);
+		out_pkt->tx_ol.l3_len = sizeof(struct ipv4_hdr);
 
 		/* Write the fragment to the output list */
 		pkts_out[out_pkt_pos] = out_pkt;
diff --git a/lib/librte_ip_frag/rte_ipv4_reassembly.c b/lib/librte_ip_frag/rte_ipv4_reassembly.c
index 06c37af..4c0104a 100644
--- a/lib/librte_ip_frag/rte_ipv4_reassembly.c
+++ b/lib/librte_ip_frag/rte_ipv4_reassembly.c
@@ -87,10 +87,10 @@ ipv4_frag_reassemble(const struct ip_frag_pkt *fp)
 
 	/* update ipv4 header for the reassmebled packet */
 	ip_hdr = (struct ipv4_hdr*)(rte_pktmbuf_mtod(m, uint8_t *) +
-		m->vlan_macip.f.l2_len);
+		m->tx_ol.l2_len);
 
 	ip_hdr->total_length = rte_cpu_to_be_16((uint16_t)(fp->total_size +
-		m->vlan_macip.f.l3_len));
+		m->tx_ol.l3_len));
 	ip_hdr->fragment_offset = (uint16_t)(ip_hdr->fragment_offset &
 		rte_cpu_to_be_16(IPV4_HDR_DF_FLAG));
 	ip_hdr->hdr_checksum = 0;
@@ -137,7 +137,7 @@ rte_ipv4_frag_reassemble_packet(struct rte_ip_frag_tbl *tbl,
 
 	ip_ofs *= IPV4_HDR_OFFSET_UNITS;
 	ip_len = (uint16_t)(rte_be_to_cpu_16(ip_hdr->total_length) -
-		mb->vlan_macip.f.l3_len);
+		mb->tx_ol.l3_len);
 
 	IP_FRAG_LOG(DEBUG, "%s:%d:\n"
 		"mbuf: %p, tms: %" PRIu64
diff --git a/lib/librte_ip_frag/rte_ipv6_reassembly.c b/lib/librte_ip_frag/rte_ipv6_reassembly.c
index dee3425..8bfe07c 100644
--- a/lib/librte_ip_frag/rte_ipv6_reassembly.c
+++ b/lib/librte_ip_frag/rte_ipv6_reassembly.c
@@ -109,7 +109,7 @@ ipv6_frag_reassemble(const struct ip_frag_pkt *fp)
 
 	/* update ipv6 header for the reassembled datagram */
 	ip_hdr = (struct ipv6_hdr *) (rte_pktmbuf_mtod(m, uint8_t *) +
-								  m->vlan_macip.f.l2_len);
+			m->tx_ol.l2_len);
 
 	ip_hdr->payload_len = rte_cpu_to_be_16(payload_len);
 
@@ -120,8 +120,7 @@ ipv6_frag_reassemble(const struct ip_frag_pkt *fp)
 	 * other headers, so we assume there are no other headers and thus update
 	 * the main IPv6 header instead.
 	 */
-	move_len = m->vlan_macip.f.l2_len + m->vlan_macip.f.l3_len -
-			sizeof(*frag_hdr);
+	move_len = m->tx_ol.l2_len + m->tx_ol.l3_len - sizeof(*frag_hdr);
 	frag_hdr = (struct ipv6_extension_fragment *) (ip_hdr + 1);
 	ip_hdr->proto = frag_hdr->next_header;
 
diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
index 01d4f6e..b4a7aea 100644
--- a/lib/librte_mbuf/rte_mbuf.h
+++ b/lib/librte_mbuf/rte_mbuf.h
@@ -112,41 +112,38 @@ extern "C" {
 #define PKT_TX_OFFLOAD_MASK (PKT_TX_VLAN_PKT | PKT_TX_IP_CKSUM | PKT_TX_L4_MASK)
 
 /** Offload features */
-union rte_vlan_macip {
-	uint32_t data;
+union rte_tx_offloads {
+	uint64_t u64;
 	struct {
+		uint8_t  l4_len;   /**< L4 Header Length */
+		uint8_t  inner_l3_len; /**< L3 tunnelling header header */
 		uint16_t l3_len:9; /**< L3 (IP) Header Length. */
 		uint16_t l2_len:7; /**< L2 (MAC) Header Length. */
-		uint16_t vlan_tci;
-		/**< VLAN Tag Control Identifier (CPU order). */
-	} f;
-};
 
-/*
- * Compare mask for vlan_macip_len.data,
- * should be in sync with rte_vlan_macip.f layout.
- * */
-#define TX_VLAN_CMP_MASK        0xFFFF0000  /**< VLAN length - 16-bits. */
-#define TX_MAC_LEN_CMP_MASK     0x0000FE00  /**< MAC length - 7-bits. */
-#define TX_IP_LEN_CMP_MASK      0x000001FF  /**< IP  length - 9-bits. */
-/**< MAC+IP  length. */
-#define TX_MACIP_LEN_CMP_MASK   (TX_MAC_LEN_CMP_MASK | TX_IP_LEN_CMP_MASK)
+		uint16_t mss;      /**< Maximum segment size */
+		uint16_t reserved;
+	};
+};
 
+/* define a set of marker types that can be used to refer to set points in the
+ * mbuf */
+typedef void    *MARKER[0];   /**< generic marker for a point in a structure */
+typedef uint64_t MARKER64[0]; /**< marker that allows us to overwrite 8 bytes
+                               * with a single assignment */
 
 /**
  * The generic rte_mbuf, containing a packet mbuf.
  */
 struct rte_mbuf {
 	/** dummy field marking start of first cache line */
-	void *cache_line0[0];
+	MARKER cache_line0;
 
 	void *buf_addr;           /**< Virtual address of segment buffer. */
 	phys_addr_t buf_physaddr; /**< Physical address of segment buffer. */
 
 	/* next 8 bytes are initialised on RX descriptor rearm */
-	uint64_t rearm_data[0]; /**< dummy element so we can get uin64_t ptrs
-	                         * to this part of the mbuf without alias error
-	                         */
+	MARKER64 rearm_data;      /**< dummy element for data set of rearm */
+
 	uint16_t buf_len;       /**< Length of segment buffer. */
 	uint16_t data_off;
 	/**
@@ -170,27 +167,42 @@ struct rte_mbuf {
 	/* remaining bytes are set on RX when pulling packet from descriptor */
 	uint64_t ol_flags;        /**< Offload features. */
 
-	__m128i rx_descriptor_fields1[0]; /**< dummy field used as marker for
-	                                   * writes in a vector driver */
+	/** dummy field used as marker for writes in a vector driver. */
+	MARKER rx_descriptor_fields1;
+
 	uint16_t packet_type;     /**< Type of packet, e.g. protocols used */
 	uint16_t data_len;        /**< Amount of data in segment buffer. */
 	uint32_t pkt_len;         /**< Total pkt len: sum of all segments. */
-	union rte_vlan_macip vlan_macip;
+	uint16_t vlan_tci0;       /**< first vlan tag control identifier */
+	uint16_t vlan_tci1;       /**< second vlan tci */
 	union {
 		uint32_t rss;       /**< RSS hash result if RSS enabled */
 		struct {
 			uint16_t hash;
 			uint16_t id;
 		} fdir;             /**< Filter identifier if FDIR enabled */
-		uint32_t sched;     /**< Hierarchical scheduler */
-	} hash;                 /**< hash information */
+		struct {
+			uint32_t lo;
+			union {
+				uint32_t hi;
+				uint32_t filter_id;
+			};
+		} fdir_i40e;    /**< i40e enhanced flow director */
+		uint32_t sched; /**< Hierarchical scheduler */
+	} filters;              /**< NIC filter information information */
+	uint32_t sequence;      /**< Packet sequence number */
 
 	/* second cache line, fields only used in slow path or on TX */
 	/** dummy field marking start of second cache line */
-	void *cache_line1[0] __rte_cache_aligned;
+	MARKER cache_line1 __rte_cache_aligned;
+
 	struct rte_mempool *pool; /**< Pool from which mbuf was allocated. */
 	struct rte_mbuf *next;    /**< Next segment of scattered packet. */
 
+	void *userdata;           /**< Pointer available for application use */
+
+	union rte_tx_offloads tx_ol; /**< Fields to enable TX offloads */
+
 	union {
 		uint8_t metadata[0];
 		uint16_t metadata16[0];
@@ -238,7 +250,6 @@ struct rte_mbuf {
  */
 #define RTE_MBUF_DIRECT(mb)     (RTE_MBUF_FROM_BADDR((mb)->buf_addr) == (mb))
 
-
 /**
  * Private data in case of pktmbuf pool.
  *
@@ -475,17 +486,20 @@ void rte_pktmbuf_pool_init(struct rte_mempool *mp, void *opaque_arg);
  * The given mbuf must have only one segment.
  *
  * @param m
- *   The packet mbuf to be resetted.
+ *   The packet mbuf to be reset.
  */
 static inline void rte_pktmbuf_reset(struct rte_mbuf *m)
 {
 	m->next = NULL;
 	m->pkt_len = 0;
-	m->vlan_macip.data = 0;
+	m->vlan_tci0 = m->vlan_tci1 = 0;
+	m->sequence = 0;
 	m->nb_segs = 1;
 	m->port = 0xff;
+	m->packet_type = 0;
 
 	m->ol_flags = 0;
+	m->tx_ol.u64 = 0;
 	m->data_off = (RTE_PKTMBUF_HEADROOM <= m->buf_len) ?
 			RTE_PKTMBUF_HEADROOM : m->buf_len;
 
@@ -538,22 +552,20 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *md)
 	    RTE_MBUF_DIRECT(mi) &&
 	    rte_mbuf_refcnt_read(mi) == 1);
 
+	/* save any needed values */
+	struct rte_mempool *pool = mi->pool;
+
+	/* increment reference count of direct mbuf */
 	rte_mbuf_refcnt_update(md, 1);
-	mi->buf_physaddr = md->buf_physaddr;
-	mi->buf_addr = md->buf_addr;
-	mi->buf_len = md->buf_len;
 
-	mi->next = md->next;
-	mi->data_off = md->data_off;
-	mi->data_len = md->data_len;
-	mi->port = md->port;
-	mi->vlan_macip = md->vlan_macip;
-	mi->hash = md->hash;
+	/* assign all fields over, then reset some values */
+	*mi = *md;
 
+	mi->pool = pool;
 	mi->next = NULL;
 	mi->pkt_len = mi->data_len;
 	mi->nb_segs = 1;
-	mi->ol_flags = md->ol_flags;
+	rte_mbuf_refcnt_set(mi, 1);
 
 	__rte_mbuf_sanity_check(mi, 1);
 	__rte_mbuf_sanity_check(md, 0);
diff --git a/lib/librte_pmd_e1000/e1000_ethdev.h b/lib/librte_pmd_e1000/e1000_ethdev.h
index 71eb5fb..6131a79 100644
--- a/lib/librte_pmd_e1000/e1000_ethdev.h
+++ b/lib/librte_pmd_e1000/e1000_ethdev.h
@@ -116,6 +116,27 @@ struct e1000_vfta {
 	uint32_t vfta[IGB_VFTA_SIZE];
 };
 
+/** Offload features for context descriptors - previously in mbuf */
+union rte_vlan_macip {
+	uint32_t data;
+	struct {
+		uint16_t l3_len:9; /**< L3 (IP) Header Length. */
+		uint16_t l2_len:7; /**< L2 (MAC) Header Length. */
+		uint16_t vlan_tci;
+		/**< VLAN Tag Control Identifier (CPU order). */
+	} f;
+};
+
+/*
+ * Compare mask for vlan_macip_len.data,
+ * should be in sync with rte_vlan_macip.f layout.
+ * */
+#define TX_VLAN_CMP_MASK        0xFFFF0000  /**< VLAN length - 16-bits. */
+#define TX_MAC_LEN_CMP_MASK     0x0000FE00  /**< MAC length - 7-bits. */
+#define TX_IP_LEN_CMP_MASK      0x000001FF  /**< IP  length - 9-bits. */
+/**< MAC+IP  length. */
+#define TX_MACIP_LEN_CMP_MASK   (TX_MAC_LEN_CMP_MASK | TX_IP_LEN_CMP_MASK)
+
 /*
  * VF data which used by PF host only
  */
diff --git a/lib/librte_pmd_e1000/em_rxtx.c b/lib/librte_pmd_e1000/em_rxtx.c
index 637141e..1bf3050 100644
--- a/lib/librte_pmd_e1000/em_rxtx.c
+++ b/lib/librte_pmd_e1000/em_rxtx.c
@@ -420,7 +420,11 @@ eth_em_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 		tx_ol_req = (uint16_t)(ol_flags & (PKT_TX_IP_CKSUM |
 							PKT_TX_L4_MASK));
 		if (tx_ol_req) {
-			hdrlen = tx_pkt->vlan_macip;
+			hdrlen = (union rte_vlan_macip){ .f = {
+					.l3_len = tx_pkt->tx_ol.l3_len,
+					.l2_len = tx_pkt->tx_ol.l2_len,
+					.vlan_tci = tx_pkt->vlan_tci0,
+				} };
 			/* If new context to be built or reuse the exist ctx. */
 			ctx = what_ctx_update(txq, tx_ol_req, hdrlen);
 
@@ -515,8 +519,7 @@ eth_em_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 		/* Set VLAN Tag offload fields. */
 		if (ol_flags & PKT_TX_VLAN_PKT) {
 			cmd_type_len |= E1000_TXD_CMD_VLE;
-			popts_spec = tx_pkt->vlan_macip.f.vlan_tci <<
-				E1000_TXD_VLAN_SHIFT;
+			popts_spec = tx_pkt->vlan_tci0 << E1000_TXD_VLAN_SHIFT;
 		}
 
 		if (tx_ol_req) {
@@ -783,7 +786,7 @@ eth_em_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 				rx_desc_error_to_pkt_flags(rxd.errors));
 
 		/* Only valid if PKT_RX_VLAN_PKT set in pkt_flags */
-		rxm->vlan_macip.f.vlan_tci = rte_le_to_cpu_16(rxd.special);
+		rxm->vlan_tci0 = rte_le_to_cpu_16(rxd.special);
 
 		/*
 		 * Store the mbuf address into the next entry of the array
@@ -1009,7 +1012,7 @@ eth_em_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 					rx_desc_error_to_pkt_flags(rxd.errors));
 
 		/* Only valid if PKT_RX_VLAN_PKT set in pkt_flags */
-		rxm->vlan_macip.f.vlan_tci = rte_le_to_cpu_16(rxd.special);
+		rxm->vlan_tci0 = rte_le_to_cpu_16(rxd.special);
 
 		/* Prefetch data of first segment, if configured to do so. */
 		rte_packet_prefetch((char *)first_seg->buf_addr +
diff --git a/lib/librte_pmd_e1000/igb_rxtx.c b/lib/librte_pmd_e1000/igb_rxtx.c
index d3e1969..490adc1 100644
--- a/lib/librte_pmd_e1000/igb_rxtx.c
+++ b/lib/librte_pmd_e1000/igb_rxtx.c
@@ -353,7 +353,7 @@ eth_igb_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 	uint16_t tx_ol_req;
 	uint32_t new_ctx = 0;
 	uint32_t ctx = 0;
-	uint32_t vlan_macip_lens;
+	union rte_vlan_macip vlan_macip_lens;
 
 	txq = tx_queue;
 	sw_ring = txq->sw_ring;
@@ -378,13 +378,15 @@ eth_igb_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 		tx_last = (uint16_t) (tx_id + tx_pkt->nb_segs - 1);
 
 		ol_flags = tx_pkt->ol_flags;
-		vlan_macip_lens = tx_pkt->vlan_macip.data;
+		vlan_macip_lens.f.vlan_tci = tx_pkt->vlan_tci0;
+		vlan_macip_lens.f.l3_len = tx_pkt->tx_ol.l3_len;
+		vlan_macip_lens.f.l2_len = tx_pkt->tx_ol.l2_len;
 		tx_ol_req = (uint16_t)(ol_flags & PKT_TX_OFFLOAD_MASK);
 
 		/* If a Context Descriptor need be built . */
 		if (tx_ol_req) {
 			ctx = what_advctx_update(txq, tx_ol_req,
-				vlan_macip_lens);
+				vlan_macip_lens.data);
 			/* Only allocate context descriptor if required*/
 			new_ctx = (ctx == IGB_CTX_NUM);
 			ctx = txq->ctx_curr;
@@ -500,7 +502,7 @@ eth_igb_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 				}
 
 				igbe_set_xmit_ctx(txq, ctx_txd, tx_ol_req,
-				    vlan_macip_lens);
+						vlan_macip_lens.data);
 
 				txe->last_id = tx_last;
 				tx_id = txe->next_id;
@@ -759,11 +761,10 @@ eth_igb_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 		rxm->data_len = pkt_len;
 		rxm->port = rxq->port_id;
 
-		rxm->hash.rss = rxd.wb.lower.hi_dword.rss;
+		rxm->filters.rss = rxd.wb.lower.hi_dword.rss;
 		hlen_type_rss = rte_le_to_cpu_32(rxd.wb.lower.lo_dword.data);
 		/* Only valid if PKT_RX_VLAN_PKT set in pkt_flags */
-		rxm->vlan_macip.f.vlan_tci =
-			rte_le_to_cpu_16(rxd.wb.upper.vlan);
+		rxm->vlan_tci0 = rte_le_to_cpu_16(rxd.wb.upper.vlan);
 
 		pkt_flags = rx_desc_hlen_type_rss_to_pkt_flags(hlen_type_rss);
 		pkt_flags = (uint16_t)(pkt_flags |
@@ -993,14 +994,13 @@ eth_igb_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 		 *      - error flags.
 		 */
 		first_seg->port = rxq->port_id;
-		first_seg->hash.rss = rxd.wb.lower.hi_dword.rss;
+		first_seg->filters.rss = rxd.wb.lower.hi_dword.rss;
 
 		/*
 		 * The vlan_tci field is only valid when PKT_RX_VLAN_PKT is
 		 * set in the pkt_flags field.
 		 */
-		first_seg->vlan_macip.f.vlan_tci =
-			rte_le_to_cpu_16(rxd.wb.upper.vlan);
+		first_seg->vlan_tci0 = rte_le_to_cpu_16(rxd.wb.upper.vlan);
 		hlen_type_rss = rte_le_to_cpu_32(rxd.wb.lower.lo_dword.data);
 		pkt_flags = rx_desc_hlen_type_rss_to_pkt_flags(hlen_type_rss);
 		pkt_flags = (uint16_t)(pkt_flags |
diff --git a/lib/librte_pmd_i40e/i40e_rxtx.c b/lib/librte_pmd_i40e/i40e_rxtx.c
index 15e7a5d..cf86973 100644
--- a/lib/librte_pmd_i40e/i40e_rxtx.c
+++ b/lib/librte_pmd_i40e/i40e_rxtx.c
@@ -614,16 +614,16 @@ i40e_rx_scan_hw_ring(struct i40e_rx_queue *rxq)
 				I40E_RXD_QW1_LENGTH_PBUF_SHIFT) - rxq->crc_len;
 			mb->data_len = pkt_len;
 			mb->pkt_len = pkt_len;
-			mb->vlan_macip.f.vlan_tci = rx_status &
+			mb->vlan_tci0 = rx_status &
 				(1 << I40E_RX_DESC_STATUS_L2TAG1P_SHIFT) ?
-			rte_le_to_cpu_16(\
-				rxdp[j].wb.qword0.lo_dword.l2tag1) : 0;
+				rte_le_to_cpu_16(\
+					rxdp[j].wb.qword0.lo_dword.l2tag1) : 0;
 			pkt_flags = i40e_rxd_status_to_pkt_flags(qword1);
 			pkt_flags |= i40e_rxd_error_to_pkt_flags(qword1);
 			pkt_flags |= i40e_rxd_ptype_to_pkt_flags(qword1);
 			mb->ol_flags = pkt_flags;
 			if (pkt_flags & PKT_RX_RSS_HASH)
-				mb->hash.rss = rte_le_to_cpu_32(\
+				mb->filters.rss = rte_le_to_cpu_32(\
 					rxdp->wb.qword0.hi_dword.rss);
 		}
 
@@ -851,7 +851,7 @@ i40e_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 		rxm->data_len = rx_packet_len;
 		rxm->port = rxq->port_id;
 
-		rxm->vlan_macip.f.vlan_tci = rx_status &
+		rxm->vlan_tci0 = rx_status &
 			(1 << I40E_RX_DESC_STATUS_L2TAG1P_SHIFT) ?
 			rte_le_to_cpu_16(rxd.wb.qword0.lo_dword.l2tag1) : 0;
 		pkt_flags = i40e_rxd_status_to_pkt_flags(qword1);
@@ -859,7 +859,7 @@ i40e_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 		pkt_flags |= i40e_rxd_ptype_to_pkt_flags(qword1);
 		rxm->ol_flags = pkt_flags;
 		if (pkt_flags & PKT_RX_RSS_HASH)
-			rxm->hash.rss =
+			rxm->filters.rss =
 				rte_le_to_cpu_32(rxd.wb.qword0.hi_dword.rss);
 
 		rx_pkts[nb_rx++] = rxm;
@@ -1004,7 +1004,7 @@ i40e_recv_scattered_pkts(void *rx_queue,
 		}
 
 		first_seg->port = rxq->port_id;
-		first_seg->vlan_macip.f.vlan_tci = (rx_status &
+		first_seg->vlan_tci0 = (rx_status &
 			(1 << I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ?
 			rte_le_to_cpu_16(rxd.wb.qword0.lo_dword.l2tag1) : 0;
 		pkt_flags = i40e_rxd_status_to_pkt_flags(qword1);
@@ -1012,7 +1012,7 @@ i40e_recv_scattered_pkts(void *rx_queue,
 		pkt_flags |= i40e_rxd_ptype_to_pkt_flags(qword1);
 		first_seg->ol_flags = pkt_flags;
 		if (pkt_flags & PKT_RX_RSS_HASH)
-			rxm->hash.rss =
+			rxm->filters.rss =
 				rte_le_to_cpu_32(rxd.wb.qword0.hi_dword.rss);
 
 		/* Prefetch data of first segment, if configured to do so. */
@@ -1107,8 +1107,8 @@ i40e_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 		RTE_MBUF_PREFETCH_TO_FREE(txe->mbuf);
 
 		ol_flags = tx_pkt->ol_flags;
-		l2_len = tx_pkt->vlan_macip.f.l2_len;
-		l3_len = tx_pkt->vlan_macip.f.l3_len;
+		l2_len = tx_pkt->tx_ol.l2_len;
+		l3_len = tx_pkt->tx_ol.l3_len;
 
 		/* Calculate the number of context descriptors needed. */
 		nb_ctx = i40e_calc_context_desc(ol_flags);
@@ -1144,7 +1144,7 @@ i40e_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 
 		/* Descriptor based VLAN insertion */
 		if (ol_flags & PKT_TX_VLAN_PKT) {
-			tx_flags |= tx_pkt->vlan_macip.f.vlan_tci <<
+			tx_flags |= tx_pkt->vlan_tci0 <<
 						I40E_TX_FLAG_L2TAG1_SHIFT;
 			tx_flags |= I40E_TX_FLAG_INSERT_VLAN;
 			td_cmd |= I40E_TX_DESC_CMD_IL2TAG1;
diff --git a/lib/librte_pmd_ixgbe/ixgbe_ethdev.h b/lib/librte_pmd_ixgbe/ixgbe_ethdev.h
index a5159e5..c2b5d2d 100644
--- a/lib/librte_pmd_ixgbe/ixgbe_ethdev.h
+++ b/lib/librte_pmd_ixgbe/ixgbe_ethdev.h
@@ -98,6 +98,27 @@
 #define IXGBE_5TUPLE_MAX_PRI            7
 #define IXGBE_5TUPLE_MIN_PRI            1
 
+/** Offload features for context descriptors - previously in mbuf */
+union rte_vlan_macip {
+	uint32_t data;
+	struct {
+		uint16_t l3_len:9; /**< L3 (IP) Header Length. */
+		uint16_t l2_len:7; /**< L2 (MAC) Header Length. */
+		uint16_t vlan_tci;
+		/**< VLAN Tag Control Identifier (CPU order). */
+	} f;
+};
+
+/*
+ * Compare mask for vlan_macip_len.data,
+ * should be in sync with rte_vlan_macip.f layout.
+ * */
+#define TX_VLAN_CMP_MASK        0xFFFF0000  /**< VLAN length - 16-bits. */
+#define TX_MAC_LEN_CMP_MASK     0x0000FE00  /**< MAC length - 7-bits. */
+#define TX_IP_LEN_CMP_MASK      0x000001FF  /**< IP  length - 9-bits. */
+/**< MAC+IP  length. */
+#define TX_MACIP_LEN_CMP_MASK   (TX_MAC_LEN_CMP_MASK | TX_IP_LEN_CMP_MASK)
+
 /*
  * Information about the fdir mode.
  */
diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx.c b/lib/librte_pmd_ixgbe/ixgbe_rxtx.c
index fadb9a0..cca44b8 100644
--- a/lib/librte_pmd_ixgbe/ixgbe_rxtx.c
+++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx.c
@@ -599,7 +599,11 @@ ixgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 		 * are needed for offload functionality.
 		 */
 		ol_flags = tx_pkt->ol_flags;
-		vlan_macip_lens = tx_pkt->vlan_macip.data;
+		vlan_macip_lens = (union rte_vlan_macip){ .f = {
+					.l3_len = tx_pkt->tx_ol.l3_len,
+					.l2_len = tx_pkt->tx_ol.l2_len,
+					.vlan_tci = tx_pkt->vlan_tci0,
+				} }.data;
 
 		/* If hardware offload required */
 		tx_ol_req = (uint16_t)(ol_flags & PKT_TX_OFFLOAD_MASK);
@@ -959,8 +963,8 @@ ixgbe_rx_scan_hw_ring(struct igb_rx_queue *rxq)
 							rxq->crc_len);
 			mb->data_len = pkt_len;
 			mb->pkt_len = pkt_len;
-			mb->vlan_macip.f.vlan_tci = rxdp[j].wb.upper.vlan;
-			mb->hash.rss = rxdp[j].wb.lower.hi_dword.rss;
+			mb->vlan_tci0 = rxdp[j].wb.upper.vlan;
+			mb->filters.rss = rxdp[j].wb.lower.hi_dword.rss;
 
 			/* convert descriptor fields to rte mbuf flags */
 			mb->ol_flags  = rx_desc_hlen_type_rss_to_pkt_flags(
@@ -1277,8 +1281,7 @@ ixgbe_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 
 		hlen_type_rss = rte_le_to_cpu_32(rxd.wb.lower.lo_dword.data);
 		/* Only valid if PKT_RX_VLAN_PKT set in pkt_flags */
-		rxm->vlan_macip.f.vlan_tci =
-			rte_le_to_cpu_16(rxd.wb.upper.vlan);
+		rxm->vlan_tci0 = rte_le_to_cpu_16(rxd.wb.upper.vlan);
 
 		pkt_flags = rx_desc_hlen_type_rss_to_pkt_flags(hlen_type_rss);
 		pkt_flags = (uint16_t)(pkt_flags |
@@ -1288,12 +1291,12 @@ ixgbe_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 		rxm->ol_flags = pkt_flags;
 
 		if (likely(pkt_flags & PKT_RX_RSS_HASH))
-			rxm->hash.rss = rxd.wb.lower.hi_dword.rss;
+			rxm->filters.rss = rxd.wb.lower.hi_dword.rss;
 		else if (pkt_flags & PKT_RX_FDIR) {
-			rxm->hash.fdir.hash =
+			rxm->filters.fdir.hash =
 				(uint16_t)((rxd.wb.lower.hi_dword.csum_ip.csum)
 					   & IXGBE_ATR_HASH_MASK);
-			rxm->hash.fdir.id = rxd.wb.lower.hi_dword.csum_ip.ip_id;
+			rxm->filters.fdir.id = rxd.wb.lower.hi_dword.csum_ip.ip_id;
 		}
 		/*
 		 * Store the mbuf address into the next entry of the array
@@ -1522,8 +1525,7 @@ ixgbe_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 		 * The vlan_tci field is only valid when PKT_RX_VLAN_PKT is
 		 * set in the pkt_flags field.
 		 */
-		first_seg->vlan_macip.f.vlan_tci =
-				rte_le_to_cpu_16(rxd.wb.upper.vlan);
+		first_seg->vlan_tci0 = rte_le_to_cpu_16(rxd.wb.upper.vlan);
 		hlen_type_rss = rte_le_to_cpu_32(rxd.wb.lower.lo_dword.data);
 		pkt_flags = rx_desc_hlen_type_rss_to_pkt_flags(hlen_type_rss);
 		pkt_flags = (uint16_t)(pkt_flags |
@@ -1533,12 +1535,12 @@ ixgbe_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 		first_seg->ol_flags = pkt_flags;
 
 		if (likely(pkt_flags & PKT_RX_RSS_HASH))
-			first_seg->hash.rss = rxd.wb.lower.hi_dword.rss;
+			first_seg->filters.rss = rxd.wb.lower.hi_dword.rss;
 		else if (pkt_flags & PKT_RX_FDIR) {
-			first_seg->hash.fdir.hash =
+			first_seg->filters.fdir.hash =
 				(uint16_t)((rxd.wb.lower.hi_dword.csum_ip.csum)
 					   & IXGBE_ATR_HASH_MASK);
-			first_seg->hash.fdir.id =
+			first_seg->filters.fdir.id =
 				rxd.wb.lower.hi_dword.csum_ip.ip_id;
 		}
 
diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
index 07314e9..ba9d050 100644
--- a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
+++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
@@ -287,9 +287,9 @@ ixgbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 		staterr = _mm_unpacklo_epi32(sterr_tmp1, sterr_tmp2);
 
 		/* D.3 copy final 3,4 data to rx_pkts */
-		_mm_storeu_si128(rx_pkts[pos+3]->rx_descriptor_fields1,
+		_mm_storeu_si128((void *)&rx_pkts[pos+3]->rx_descriptor_fields1,
 				pkt_mb4);
-		_mm_storeu_si128(rx_pkts[pos+2]->rx_descriptor_fields1,
+		_mm_storeu_si128((void *)&rx_pkts[pos+2]->rx_descriptor_fields1,
 				pkt_mb3);
 
 		/* D.2 pkt 1,2 set in_port/nb_seg and remove crc */
@@ -301,9 +301,9 @@ ixgbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 		staterr = _mm_packs_epi32(staterr, zero);
 
 		/* D.3 copy final 1,2 data to rx_pkts */
-		_mm_storeu_si128(rx_pkts[pos+1]->rx_descriptor_fields1,
+		_mm_storeu_si128((void *)&rx_pkts[pos+1]->rx_descriptor_fields1,
 				pkt_mb2);
-		_mm_storeu_si128(rx_pkts[pos]->rx_descriptor_fields1,
+		_mm_storeu_si128((void *)&rx_pkts[pos]->rx_descriptor_fields1,
 				pkt_mb1);
 
 		/* C.4 calc avaialbe number of desc */
diff --git a/lib/librte_pmd_vmxnet3/vmxnet3_rxtx.c b/lib/librte_pmd_vmxnet3/vmxnet3_rxtx.c
index f18fad6..e657a97 100644
--- a/lib/librte_pmd_vmxnet3/vmxnet3_rxtx.c
+++ b/lib/librte_pmd_vmxnet3/vmxnet3_rxtx.c
@@ -549,7 +549,7 @@ vmxnet3_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 					       rte_pktmbuf_mtod(rxm, void *));
 #endif
 				/* Copy vlan tag in packet buffer */
-				rxm->vlan_macip.f.vlan_tci =
+				rxm->vlan_tci0 =
 					rte_le_to_cpu_16((uint16_t)rcd->tci);
 
 			} else
@@ -562,7 +562,7 @@ vmxnet3_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 			rxm->pkt_len = (uint16_t)rcd->len;
 			rxm->data_len = (uint16_t)rcd->len;
 			rxm->port = rxq->port_id;
-			rxm->vlan_macip.f.vlan_tci = 0;
+			rxm->vlan_tci0 = 0;
 			rxm->data_off = RTE_PKTMBUF_HEADROOM;
 
 			rx_pkts[nb_rx++] = rxm;
diff --git a/lib/librte_sched/rte_sched.h b/lib/librte_sched/rte_sched.h
index e6bba22..11f63fc 100644
--- a/lib/librte_sched/rte_sched.h
+++ b/lib/librte_sched/rte_sched.h
@@ -195,10 +195,12 @@ struct rte_sched_port_params {
 #endif
 };
 
-/** Path through the scheduler hierarchy used by the scheduler enqueue operation to
-identify the destination queue for the current packet. Stored in the field hash.sched
-of struct rte_mbuf of each packet, typically written by the classification stage and read by
-scheduler enqueue.*/
+/**
+ * Path through the scheduler hierarchy used by the scheduler enqueue operation
+ * to identify the destination queue for the current packet. Stored in the field
+ * filters.sched of struct rte_mbuf of each packet, typically written by the
+ * classification stage and read by scheduler enqueue.
+ */
 struct rte_sched_port_hierarchy {
 	uint32_t queue:2;                /**< Queue ID (0 .. 3) */
 	uint32_t traffic_class:2;        /**< Traffic class ID (0 .. 3)*/
@@ -352,7 +354,8 @@ static inline void
 rte_sched_port_pkt_write(struct rte_mbuf *pkt,
 	uint32_t subport, uint32_t pipe, uint32_t traffic_class, uint32_t queue, enum rte_meter_color color)
 {
-	struct rte_sched_port_hierarchy *sched = (struct rte_sched_port_hierarchy *) &pkt->hash.sched;
+	struct rte_sched_port_hierarchy *sched =
+			(struct rte_sched_port_hierarchy *) &pkt->filters.sched;
 
 	sched->color = (uint32_t) color;
 	sched->subport = subport;
@@ -381,7 +384,8 @@ rte_sched_port_pkt_write(struct rte_mbuf *pkt,
 static inline void
 rte_sched_port_pkt_read_tree_path(struct rte_mbuf *pkt, uint32_t *subport, uint32_t *pipe, uint32_t *traffic_class, uint32_t *queue)
 {
-	struct rte_sched_port_hierarchy *sched = (struct rte_sched_port_hierarchy *) &pkt->hash.sched;
+	struct rte_sched_port_hierarchy *sched =
+			(struct rte_sched_port_hierarchy *) &pkt->filters.sched;
 
 	*subport = sched->subport;
 	*pipe = sched->pipe;
@@ -392,7 +396,8 @@ rte_sched_port_pkt_read_tree_path(struct rte_mbuf *pkt, uint32_t *subport, uint3
 static inline enum rte_meter_color
 rte_sched_port_pkt_read_color(struct rte_mbuf *pkt)
 {
-	struct rte_sched_port_hierarchy *sched = (struct rte_sched_port_hierarchy *) &pkt->hash.sched;
+	struct rte_sched_port_hierarchy *sched =
+			(struct rte_sched_port_hierarchy *) &pkt->filters.sched;
 
 	return (enum rte_meter_color) sched->color;
 }
-- 
1.9.3