New upstream version 17.11-rc3

Change-Id: I6a5baa40612fe0c20f30b5fa773a6cbbac63a685
Signed-off-by: Luca Boccassi <luca.boccassi@gmail.com>

14 files changed, 511 insertions, 59 deletions

diff --git a/examples/l3fwd/l3fwd.h b/examples/l3fwd/l3fwd.h
index 011ba148..4bb15943 100644
--- a/examples/l3fwd/l3fwd.h
+++ b/examples/l3fwd/l3fwd.h
@@ -83,7 +83,7 @@ struct mbuf_table {
 };
 
 struct lcore_rx_queue {
-	uint8_t port_id;
+	uint16_t port_id;
 	uint8_t queue_id;
 } __rte_cache_aligned;
 
@@ -117,7 +117,7 @@ extern struct lcore_conf lcore_conf[RTE_MAX_LCORE];
 
 /* Send burst of packets on an output interface */
 static inline int
-send_burst(struct lcore_conf *qconf, uint16_t n, uint8_t port)
+send_burst(struct lcore_conf *qconf, uint16_t n, uint16_t port)
 {
 	struct rte_mbuf **m_table;
 	int ret;
@@ -139,7 +139,7 @@ send_burst(struct lcore_conf *qconf, uint16_t n, uint8_t port)
 /* Enqueue a single packet, and send burst if queue is filled */
 static inline int
 send_single_packet(struct lcore_conf *qconf,
-		struct rte_mbuf *m, uint8_t port)
+		   struct rte_mbuf *m, uint16_t port)
 {
 	uint16_t len;
 
@@ -212,11 +212,11 @@ int
 lpm_check_ptype(int portid);
 
 uint16_t
-em_cb_parse_ptype(uint8_t port, uint16_t queue, struct rte_mbuf *pkts[],
+em_cb_parse_ptype(uint16_t port, uint16_t queue, struct rte_mbuf *pkts[],
 		  uint16_t nb_pkts, uint16_t max_pkts, void *user_param);
 
 uint16_t
-lpm_cb_parse_ptype(uint8_t port, uint16_t queue, struct rte_mbuf *pkts[],
+lpm_cb_parse_ptype(uint16_t port, uint16_t queue, struct rte_mbuf *pkts[],
 		   uint16_t nb_pkts, uint16_t max_pkts, void *user_param);
 
 int
diff --git a/examples/l3fwd/l3fwd_altivec.h b/examples/l3fwd/l3fwd_altivec.h
new file mode 100644
index 00000000..a1d25eaa
--- /dev/null
+++ b/examples/l3fwd/l3fwd_altivec.h
@@ -0,0 +1,284 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2016 Intel Corporation. All rights reserved.
+ *   Copyright(c) 2017 IBM Corporation.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+
+#ifndef _L3FWD_ALTIVEC_H_
+#define _L3FWD_ALTIVEC_H_
+
+#include "l3fwd.h"
+#include "l3fwd_common.h"
+
+/*
+ * Update source and destination MAC addresses in the ethernet header.
+ * Perform RFC1812 checks and updates for IPV4 packets.
+ */
+static inline void
+processx4_step3(struct rte_mbuf *pkt[FWDSTEP], uint16_t dst_port[FWDSTEP])
+{
+	vector unsigned int te[FWDSTEP];
+	vector unsigned int ve[FWDSTEP];
+	vector unsigned int *p[FWDSTEP];
+
+	p[0] = rte_pktmbuf_mtod(pkt[0], vector unsigned int *);
+	p[1] = rte_pktmbuf_mtod(pkt[1], vector unsigned int *);
+	p[2] = rte_pktmbuf_mtod(pkt[2], vector unsigned int *);
+	p[3] = rte_pktmbuf_mtod(pkt[3], vector unsigned int *);
+
+	ve[0] = (vector unsigned int)val_eth[dst_port[0]];
+	te[0] = *p[0];
+
+	ve[1] = (vector unsigned int)val_eth[dst_port[1]];
+	te[1] = *p[1];
+
+	ve[2] = (vector unsigned int)val_eth[dst_port[2]];
+	te[2] = *p[2];
+
+	ve[3] = (vector unsigned int)val_eth[dst_port[3]];
+	te[3] = *p[3];
+
+	/* Update first 12 bytes, keep rest bytes intact. */
+	te[0] = (vector unsigned int)vec_sel(
+			(vector unsigned short)ve[0],
+			(vector unsigned short)te[0],
+			(vector unsigned short) {0, 0, 0, 0,
+						0, 0, 0xffff, 0xffff});
+
+	te[1] = (vector unsigned int)vec_sel(
+			(vector unsigned short)ve[1],
+			(vector unsigned short)te[1],
+			(vector unsigned short) {0, 0, 0, 0,
+						0, 0, 0xffff, 0xffff});
+
+	te[2] = (vector unsigned int)vec_sel(
+			(vector unsigned short)ve[2],
+			(vector unsigned short)te[2],
+			(vector unsigned short) {0, 0, 0, 0, 0,
+						0, 0xffff, 0xffff});
+
+	te[3] = (vector unsigned int)vec_sel(
+			(vector unsigned short)ve[3],
+			(vector unsigned short)te[3],
+			(vector unsigned short) {0, 0, 0, 0,
+						0, 0, 0xffff, 0xffff});
+
+	*p[0] = te[0];
+	*p[1] = te[1];
+	*p[2] = te[2];
+	*p[3] = te[3];
+
+	rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[0] + 1),
+		&dst_port[0], pkt[0]->packet_type);
+	rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[1] + 1),
+		&dst_port[1], pkt[1]->packet_type);
+	rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[2] + 1),
+		&dst_port[2], pkt[2]->packet_type);
+	rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[3] + 1),
+		&dst_port[3], pkt[3]->packet_type);
+}
+
+/*
+ * Group consecutive packets with the same destination port in bursts of 4.
+ * Suppose we have array of destination ports:
+ * dst_port[] = {a, b, c, d,, e, ... }
+ * dp1 should contain: <a, b, c, d>, dp2: <b, c, d, e>.
+ * We doing 4 comparisons at once and the result is 4 bit mask.
+ * This mask is used as an index into prebuild array of pnum values.
+ */
+static inline uint16_t *
+port_groupx4(uint16_t pn[FWDSTEP + 1], uint16_t *lp, vector unsigned short dp1,
+	vector unsigned short dp2)
+{
+	union {
+		uint16_t u16[FWDSTEP + 1];
+		uint64_t u64;
+	} *pnum = (void *)pn;
+
+	int32_t v;
+
+	v = vec_any_eq(dp1, dp2);
+
+
+	/* update last port counter. */
+	lp[0] += gptbl[v].lpv;
+
+	/* if dest port value has changed. */
+	if (v != GRPMSK) {
+		pnum->u64 = gptbl[v].pnum;
+		pnum->u16[FWDSTEP] = 1;
+		lp = pnum->u16 + gptbl[v].idx;
+	}
+
+	return lp;
+}
+
+/**
+ * Process one packet:
+ * Update source and destination MAC addresses in the ethernet header.
+ * Perform RFC1812 checks and updates for IPV4 packets.
+ */
+static inline void
+process_packet(struct rte_mbuf *pkt, uint16_t *dst_port)
+{
+	struct ether_hdr *eth_hdr;
+	vector unsigned int te, ve;
+
+	eth_hdr = rte_pktmbuf_mtod(pkt, struct ether_hdr *);
+
+	te = *(vector unsigned int *)eth_hdr;
+	ve = (vector unsigned int)val_eth[dst_port[0]];
+
+	rfc1812_process((struct ipv4_hdr *)(eth_hdr + 1), dst_port,
+			pkt->packet_type);
+
+	/* dynamically vec_sel te and ve for MASK_ETH (0x3f) */
+	te = (vector unsigned int)vec_sel(
+		(vector unsigned short)ve,
+		(vector unsigned short)te,
+		(vector unsigned short){0, 0, 0, 0,
+					0, 0, 0xffff, 0xffff});
+
+	*(vector unsigned int *)eth_hdr = te;
+}
+
+/**
+ * Send packets burst from pkts_burst to the ports in dst_port array
+ */
+static __rte_always_inline void
+send_packets_multi(struct lcore_conf *qconf, struct rte_mbuf **pkts_burst,
+		uint16_t dst_port[MAX_PKT_BURST], int nb_rx)
+{
+	int32_t k;
+	int j = 0;
+	uint16_t dlp;
+	uint16_t *lp;
+	uint16_t pnum[MAX_PKT_BURST + 1];
+
+	/*
+	 * Finish packet processing and group consecutive
+	 * packets with the same destination port.
+	 */
+	k = RTE_ALIGN_FLOOR(nb_rx, FWDSTEP);
+	if (k != 0) {
+		vector unsigned short dp1, dp2;
+
+		lp = pnum;
+		lp[0] = 1;
+
+		processx4_step3(pkts_burst, dst_port);
+
+		/* dp1: <d[0], d[1], d[2], d[3], ... > */
+		dp1 = *(vector unsigned short *)dst_port;
+
+		for (j = FWDSTEP; j != k; j += FWDSTEP) {
+			processx4_step3(&pkts_burst[j], &dst_port[j]);
+
+			/*
+			 * dp2:
+			 * <d[j-3], d[j-2], d[j-1], d[j], ... >
+			 */
+			dp2 = *((vector unsigned short *)
+					&dst_port[j - FWDSTEP + 1]);
+			lp  = port_groupx4(&pnum[j - FWDSTEP], lp, dp1, dp2);
+
+			/*
+			 * dp1:
+			 * <d[j], d[j+1], d[j+2], d[j+3], ... >
+			 */
+			dp1 = vec_sro(dp2, (vector unsigned char) {
+				0, 0, 0, 0, 0, 0, 0, 0,
+				0, 0, 0, (FWDSTEP - 1) * sizeof(dst_port[0])});
+		}
+
+		/*
+		 * dp2: <d[j-3], d[j-2], d[j-1], d[j-1], ... >
+		 */
+		dp2 = vec_perm(dp1, (vector unsigned short){},
+				(vector unsigned char){0xf9});
+		lp  = port_groupx4(&pnum[j - FWDSTEP], lp, dp1, dp2);
+
+		/*
+		 * remove values added by the last repeated
+		 * dst port.
+		 */
+		lp[0]--;
+		dlp = dst_port[j - 1];
+	} else {
+		/* set dlp and lp to the never used values. */
+		dlp = BAD_PORT - 1;
+		lp = pnum + MAX_PKT_BURST;
+	}
+
+	/* Process up to last 3 packets one by one. */
+	switch (nb_rx % FWDSTEP) {
+	case 3:
+		process_packet(pkts_burst[j], dst_port + j);
+		GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j);
+		j++;
+		/* fall-through */
+	case 2:
+		process_packet(pkts_burst[j], dst_port + j);
+		GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j);
+		j++;
+		/* fall-through */
+	case 1:
+		process_packet(pkts_burst[j], dst_port + j);
+		GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j);
+		j++;
+	}
+
+	/*
+	 * Send packets out, through destination port.
+	 * Consecutive packets with the same destination port
+	 * are already grouped together.
+	 * If destination port for the packet equals BAD_PORT,
+	 * then free the packet without sending it out.
+	 */
+	for (j = 0; j < nb_rx; j += k) {
+
+		int32_t m;
+		uint16_t pn;
+
+		pn = dst_port[j];
+		k = pnum[j];
+
+		if (likely(pn != BAD_PORT))
+			send_packetsx4(qconf, pn, pkts_burst + j, k);
+		else
+			for (m = j; m != j + k; m++)
+				rte_pktmbuf_free(pkts_burst[m]);
+
+	}
+}
+
+#endif /* _L3FWD_ALTIVEC_H_ */
diff --git a/examples/l3fwd/l3fwd_common.h b/examples/l3fwd/l3fwd_common.h
index 2867365d..7002a43a 100644
--- a/examples/l3fwd/l3fwd_common.h
+++ b/examples/l3fwd/l3fwd_common.h
@@ -207,7 +207,7 @@ static const struct {
 };
 
 static __rte_always_inline void
-send_packetsx4(struct lcore_conf *qconf, uint8_t port, struct rte_mbuf *m[],
+send_packetsx4(struct lcore_conf *qconf, uint16_t port, struct rte_mbuf *m[],
 		uint32_t num)
 {
 	uint32_t len, j, n;
diff --git a/examples/l3fwd/l3fwd_em.c b/examples/l3fwd/l3fwd_em.c
index 53d081bd..2b7c173b 100644
--- a/examples/l3fwd/l3fwd_em.c
+++ b/examples/l3fwd/l3fwd_em.c
@@ -274,8 +274,8 @@ em_mask_key(void *key, xmm_t mask)
 #error No vector engine (SSE, NEON, ALTIVEC) available, check your toolchain
 #endif
 
-static inline uint8_t
-em_get_ipv4_dst_port(void *ipv4_hdr, uint8_t portid, void *lookup_struct)
+static inline uint16_t
+em_get_ipv4_dst_port(void *ipv4_hdr, uint16_t portid, void *lookup_struct)
 {
 	int ret = 0;
 	union ipv4_5tuple_host key;
@@ -292,11 +292,11 @@ em_get_ipv4_dst_port(void *ipv4_hdr, uint8_t portid, void *lookup_struct)
 
 	/* Find destination port */
 	ret = rte_hash_lookup(ipv4_l3fwd_lookup_struct, (const void *)&key);
-	return (uint8_t)((ret < 0) ? portid : ipv4_l3fwd_out_if[ret]);
+	return (ret < 0) ? portid : ipv4_l3fwd_out_if[ret];
 }
 
-static inline uint8_t
-em_get_ipv6_dst_port(void *ipv6_hdr,  uint8_t portid, void *lookup_struct)
+static inline uint16_t
+em_get_ipv6_dst_port(void *ipv6_hdr, uint16_t portid, void *lookup_struct)
 {
 	int ret = 0;
 	union ipv6_5tuple_host key;
@@ -325,7 +325,7 @@ em_get_ipv6_dst_port(void *ipv6_hdr,  uint8_t portid, void *lookup_struct)
 
 	/* Find destination port */
 	ret = rte_hash_lookup(ipv6_l3fwd_lookup_struct, (const void *)&key);
-	return (uint8_t)((ret < 0) ? portid : ipv6_l3fwd_out_if[ret]);
+	return (ret < 0) ? portid : ipv6_l3fwd_out_if[ret];
 }
 
 #if defined RTE_ARCH_X86 || defined RTE_MACHINE_CPUFLAG_NEON
@@ -628,7 +628,7 @@ em_parse_ptype(struct rte_mbuf *m)
 }
 
 uint16_t
-em_cb_parse_ptype(uint8_t port __rte_unused, uint16_t queue __rte_unused,
+em_cb_parse_ptype(uint16_t port __rte_unused, uint16_t queue __rte_unused,
 		  struct rte_mbuf *pkts[], uint16_t nb_pkts,
 		  uint16_t max_pkts __rte_unused,
 		  void *user_param __rte_unused)
@@ -649,7 +649,8 @@ em_main_loop(__attribute__((unused)) void *dummy)
 	unsigned lcore_id;
 	uint64_t prev_tsc, diff_tsc, cur_tsc;
 	int i, nb_rx;
-	uint8_t portid, queueid;
+	uint8_t queueid;
+	uint16_t portid;
 	struct lcore_conf *qconf;
 	const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) /
 		US_PER_S * BURST_TX_DRAIN_US;
@@ -671,7 +672,7 @@ em_main_loop(__attribute__((unused)) void *dummy)
 		portid = qconf->rx_queue_list[i].port_id;
 		queueid = qconf->rx_queue_list[i].queue_id;
 		RTE_LOG(INFO, L3FWD,
-			" -- lcoreid=%u portid=%hhu rxqueueid=%hhu\n",
+			" -- lcoreid=%u portid=%u rxqueueid=%hhu\n",
 			lcore_id, portid, queueid);
 	}
 
diff --git a/examples/l3fwd/l3fwd_em.h b/examples/l3fwd/l3fwd_em.h
index d509a1fc..302291d7 100644
--- a/examples/l3fwd/l3fwd_em.h
+++ b/examples/l3fwd/l3fwd_em.h
@@ -35,12 +35,12 @@
 #define __L3FWD_EM_H__
 
 static __rte_always_inline void
-l3fwd_em_simple_forward(struct rte_mbuf *m, uint8_t portid,
+l3fwd_em_simple_forward(struct rte_mbuf *m, uint16_t portid,
 		struct lcore_conf *qconf)
 {
 	struct ether_hdr *eth_hdr;
 	struct ipv4_hdr *ipv4_hdr;
-	uint8_t dst_port;
+	uint16_t dst_port;
 	uint32_t tcp_or_udp;
 	uint32_t l3_ptypes;
 
@@ -112,7 +112,7 @@ l3fwd_em_simple_forward(struct rte_mbuf *m, uint8_t portid,
  */
 static inline void
 l3fwd_em_no_opt_send_packets(int nb_rx, struct rte_mbuf **pkts_burst,
-			uint8_t portid, struct lcore_conf *qconf)
+			uint16_t portid, struct lcore_conf *qconf)
 {
 	int32_t j;
 
diff --git a/examples/l3fwd/l3fwd_em_hlm.h b/examples/l3fwd/l3fwd_em_hlm.h
index 520672d5..9d7afe05 100644
--- a/examples/l3fwd/l3fwd_em_hlm.h
+++ b/examples/l3fwd/l3fwd_em_hlm.h
@@ -52,7 +52,7 @@
 
 static __rte_always_inline void
 em_get_dst_port_ipv4xN(struct lcore_conf *qconf, struct rte_mbuf *m[],
-		uint8_t portid, uint16_t dst_port[])
+		uint16_t portid, uint16_t dst_port[])
 {
 	int i;
 	int32_t ret[EM_HASH_LOOKUP_COUNT];
@@ -68,7 +68,7 @@ em_get_dst_port_ipv4xN(struct lcore_conf *qconf, struct rte_mbuf *m[],
 			     EM_HASH_LOOKUP_COUNT, ret);
 
 	for (i = 0; i < EM_HASH_LOOKUP_COUNT; i++) {
-		dst_port[i] = (uint8_t) ((ret[i] < 0) ?
+		dst_port[i] = ((ret[i] < 0) ?
 				portid : ipv4_l3fwd_out_if[ret[i]]);
 
 		if (dst_port[i] >= RTE_MAX_ETHPORTS ||
@@ -79,7 +79,7 @@ em_get_dst_port_ipv4xN(struct lcore_conf *qconf, struct rte_mbuf *m[],
 
 static __rte_always_inline void
 em_get_dst_port_ipv6xN(struct lcore_conf *qconf, struct rte_mbuf *m[],
-		uint8_t portid, uint16_t dst_port[])
+		uint16_t portid, uint16_t dst_port[])
 {
 	int i;
 	int32_t ret[EM_HASH_LOOKUP_COUNT];
@@ -95,7 +95,7 @@ em_get_dst_port_ipv6xN(struct lcore_conf *qconf, struct rte_mbuf *m[],
 			     EM_HASH_LOOKUP_COUNT, ret);
 
 	for (i = 0; i < EM_HASH_LOOKUP_COUNT; i++) {
-		dst_port[i] = (uint8_t) ((ret[i] < 0) ?
+		dst_port[i] = ((ret[i] < 0) ?
 				portid : ipv6_l3fwd_out_if[ret[i]]);
 
 		if (dst_port[i] >= RTE_MAX_ETHPORTS ||
@@ -106,9 +106,9 @@ em_get_dst_port_ipv6xN(struct lcore_conf *qconf, struct rte_mbuf *m[],
 
 static __rte_always_inline uint16_t
 em_get_dst_port(const struct lcore_conf *qconf, struct rte_mbuf *pkt,
-		uint8_t portid)
+		uint16_t portid)
 {
-	uint8_t next_hop;
+	uint16_t next_hop;
 	struct ipv4_hdr *ipv4_hdr;
 	struct ipv6_hdr *ipv6_hdr;
 	uint32_t tcp_or_udp;
@@ -158,7 +158,7 @@ em_get_dst_port(const struct lcore_conf *qconf, struct rte_mbuf *pkt,
  */
 static inline void
 l3fwd_em_send_packets(int nb_rx, struct rte_mbuf **pkts_burst,
-		uint8_t portid, struct lcore_conf *qconf)
+		uint16_t portid, struct lcore_conf *qconf)
 {
 	int32_t i, j, pos;
 	uint16_t dst_port[MAX_PKT_BURST];
diff --git a/examples/l3fwd/l3fwd_em_sequential.h b/examples/l3fwd/l3fwd_em_sequential.h
index cb7c2abb..fa89f0f3 100644
--- a/examples/l3fwd/l3fwd_em_sequential.h
+++ b/examples/l3fwd/l3fwd_em_sequential.h
@@ -51,7 +51,7 @@
 
 static __rte_always_inline uint16_t
 em_get_dst_port(const struct lcore_conf *qconf, struct rte_mbuf *pkt,
-		uint8_t portid)
+		uint16_t portid)
 {
 	uint8_t next_hop;
 	struct ipv4_hdr *ipv4_hdr;
@@ -103,7 +103,7 @@ em_get_dst_port(const struct lcore_conf *qconf, struct rte_mbuf *pkt,
  */
 static inline void
 l3fwd_em_send_packets(int nb_rx, struct rte_mbuf **pkts_burst,
-			uint8_t portid, struct lcore_conf *qconf)
+			uint16_t portid, struct lcore_conf *qconf)
 {
 	int32_t i, j;
 	uint16_t dst_port[MAX_PKT_BURST];
diff --git a/examples/l3fwd/l3fwd_lpm.c b/examples/l3fwd/l3fwd_lpm.c
index ff1e4035..2d0e1724 100644
--- a/examples/l3fwd/l3fwd_lpm.c
+++ b/examples/l3fwd/l3fwd_lpm.c
@@ -105,7 +105,7 @@ struct rte_lpm *ipv4_l3fwd_lpm_lookup_struct[NB_SOCKETS];
 struct rte_lpm6 *ipv6_l3fwd_lpm_lookup_struct[NB_SOCKETS];
 
 static inline uint16_t
-lpm_get_ipv4_dst_port(void *ipv4_hdr,  uint8_t portid, void *lookup_struct)
+lpm_get_ipv4_dst_port(void *ipv4_hdr, uint16_t portid, void *lookup_struct)
 {
 	uint32_t next_hop;
 	struct rte_lpm *ipv4_l3fwd_lookup_struct =
@@ -117,7 +117,7 @@ lpm_get_ipv4_dst_port(void *ipv4_hdr,  uint8_t portid, void *lookup_struct)
 }
 
 static inline uint16_t
-lpm_get_ipv6_dst_port(void *ipv6_hdr,  uint8_t portid, void *lookup_struct)
+lpm_get_ipv6_dst_port(void *ipv6_hdr, uint16_t portid, void *lookup_struct)
 {
 	uint32_t next_hop;
 	struct rte_lpm6 *ipv6_l3fwd_lookup_struct =
@@ -130,7 +130,7 @@ lpm_get_ipv6_dst_port(void *ipv6_hdr,  uint8_t portid, void *lookup_struct)
 
 static __rte_always_inline uint16_t
 lpm_get_dst_port(const struct lcore_conf *qconf, struct rte_mbuf *pkt,
-		uint8_t portid)
+		uint16_t portid)
 {
 	struct ipv6_hdr *ipv6_hdr;
 	struct ipv4_hdr *ipv4_hdr;
@@ -162,7 +162,7 @@ lpm_get_dst_port(const struct lcore_conf *qconf, struct rte_mbuf *pkt,
  */
 static __rte_always_inline uint16_t
 lpm_get_dst_port_with_ipv4(const struct lcore_conf *qconf, struct rte_mbuf *pkt,
-	uint32_t dst_ipv4, uint8_t portid)
+	uint32_t dst_ipv4, uint16_t portid)
 {
 	uint32_t next_hop;
 	struct ipv6_hdr *ipv6_hdr;
@@ -191,6 +191,8 @@ lpm_get_dst_port_with_ipv4(const struct lcore_conf *qconf, struct rte_mbuf *pkt,
 #include "l3fwd_lpm_sse.h"
 #elif defined RTE_MACHINE_CPUFLAG_NEON
 #include "l3fwd_lpm_neon.h"
+#elif defined(RTE_ARCH_PPC_64)
+#include "l3fwd_lpm_altivec.h"
 #else
 #include "l3fwd_lpm.h"
 #endif
@@ -203,7 +205,8 @@ lpm_main_loop(__attribute__((unused)) void *dummy)
 	unsigned lcore_id;
 	uint64_t prev_tsc, diff_tsc, cur_tsc;
 	int i, nb_rx;
-	uint8_t portid, queueid;
+	uint16_t portid;
+	uint8_t queueid;
 	struct lcore_conf *qconf;
 	const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) /
 		US_PER_S * BURST_TX_DRAIN_US;
@@ -225,7 +228,7 @@ lpm_main_loop(__attribute__((unused)) void *dummy)
 		portid = qconf->rx_queue_list[i].port_id;
 		queueid = qconf->rx_queue_list[i].queue_id;
 		RTE_LOG(INFO, L3FWD,
-			" -- lcoreid=%u portid=%hhu rxqueueid=%hhu\n",
+			" -- lcoreid=%u portid=%u rxqueueid=%hhu\n",
 			lcore_id, portid, queueid);
 	}
 
@@ -263,7 +266,8 @@ lpm_main_loop(__attribute__((unused)) void *dummy)
 			if (nb_rx == 0)
 				continue;
 
-#if defined RTE_ARCH_X86 || defined RTE_MACHINE_CPUFLAG_NEON
+#if defined RTE_ARCH_X86 || defined RTE_MACHINE_CPUFLAG_NEON \
+			 || defined RTE_ARCH_PPC_64
 			l3fwd_lpm_send_packets(nb_rx, pkts_burst,
 						portid, qconf);
 #else
@@ -413,7 +417,7 @@ lpm_parse_ptype(struct rte_mbuf *m)
 }
 
 uint16_t
-lpm_cb_parse_ptype(uint8_t port __rte_unused, uint16_t queue __rte_unused,
+lpm_cb_parse_ptype(uint16_t port __rte_unused, uint16_t queue __rte_unused,
 		   struct rte_mbuf *pkts[], uint16_t nb_pkts,
 		   uint16_t max_pkts __rte_unused,
 		   void *user_param __rte_unused)
diff --git a/examples/l3fwd/l3fwd_lpm.h b/examples/l3fwd/l3fwd_lpm.h
index 55c3e832..53b7fc80 100644
--- a/examples/l3fwd/l3fwd_lpm.h
+++ b/examples/l3fwd/l3fwd_lpm.h
@@ -35,7 +35,7 @@
 #define __L3FWD_LPM_H__
 
 static __rte_always_inline void
-l3fwd_lpm_simple_forward(struct rte_mbuf *m, uint8_t portid,
+l3fwd_lpm_simple_forward(struct rte_mbuf *m, uint16_t portid,
 		struct lcore_conf *qconf)
 {
 	struct ether_hdr *eth_hdr;
@@ -104,7 +104,7 @@ l3fwd_lpm_simple_forward(struct rte_mbuf *m, uint8_t portid,
 
 static inline void
 l3fwd_lpm_no_opt_send_packets(int nb_rx, struct rte_mbuf **pkts_burst,
-				uint8_t portid, struct lcore_conf *qconf)
+				uint16_t portid, struct lcore_conf *qconf)
 {
 	int32_t j;
 
diff --git a/examples/l3fwd/l3fwd_lpm_altivec.h b/examples/l3fwd/l3fwd_lpm_altivec.h
new file mode 100644
index 00000000..36ca983f
--- /dev/null
+++ b/examples/l3fwd/l3fwd_lpm_altivec.h
@@ -0,0 +1,164 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
+ *   Copyright(c) 2017 IBM Corporation.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __L3FWD_LPM_ALTIVEC_H__
+#define __L3FWD_LPM_ALTIVEC_H__
+
+#include "l3fwd_altivec.h"
+
+/*
+ * Read packet_type and destination IPV4 addresses from 4 mbufs.
+ */
+static inline void
+processx4_step1(struct rte_mbuf *pkt[FWDSTEP],
+		vector unsigned int *dip,
+		uint32_t *ipv4_flag)
+{
+	struct ipv4_hdr *ipv4_hdr;
+	struct ether_hdr *eth_hdr;
+	uint32_t x0, x1, x2, x3;
+
+	eth_hdr = rte_pktmbuf_mtod(pkt[0], struct ether_hdr *);
+	ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
+	x0 = ipv4_hdr->dst_addr;
+	ipv4_flag[0] = pkt[0]->packet_type & RTE_PTYPE_L3_IPV4;
+
+	rte_compiler_barrier();
+	eth_hdr = rte_pktmbuf_mtod(pkt[1], struct ether_hdr *);
+	ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
+	x1 = ipv4_hdr->dst_addr;
+	ipv4_flag[0] &= pkt[1]->packet_type;
+
+	rte_compiler_barrier();
+	eth_hdr = rte_pktmbuf_mtod(pkt[2], struct ether_hdr *);
+	ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
+	x2 = ipv4_hdr->dst_addr;
+	ipv4_flag[0] &= pkt[2]->packet_type;
+
+	rte_compiler_barrier();
+	eth_hdr = rte_pktmbuf_mtod(pkt[3], struct ether_hdr *);
+	ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
+	x3 = ipv4_hdr->dst_addr;
+	ipv4_flag[0] &= pkt[3]->packet_type;
+
+	rte_compiler_barrier();
+	dip[0] = (vector unsigned int){x0, x1, x2, x3};
+}
+
+/*
+ * Lookup into LPM for destination port.
+ * If lookup fails, use incoming port (portid) as destination port.
+ */
+static inline void
+processx4_step2(const struct lcore_conf *qconf,
+		vector unsigned int dip,
+		uint32_t ipv4_flag,
+		uint8_t portid,
+		struct rte_mbuf *pkt[FWDSTEP],
+		uint16_t dprt[FWDSTEP])
+{
+	rte_xmm_t dst;
+	const vector unsigned char bswap_mask = (vector unsigned char){
+							3, 2, 1, 0,
+							7, 6, 5, 4,
+							11, 10, 9, 8,
+							15, 14, 13, 12};
+
+	/* Byte swap 4 IPV4 addresses. */
+	dip = (vector unsigned int)vec_perm(*(vector unsigned char *)&dip,
+					(vector unsigned char){}, bswap_mask);
+
+	/* if all 4 packets are IPV4. */
+	if (likely(ipv4_flag)) {
+		rte_lpm_lookupx4(qconf->ipv4_lookup_struct, (xmm_t)dip,
+			(uint32_t *)&dst, portid);
+		/* get rid of unused upper 16 bit for each dport. */
+		dst.x = (xmm_t)vec_packs(dst.x, dst.x);
+		*(uint64_t *)dprt = dst.u64[0];
+	} else {
+		dst.x = (xmm_t)dip;
+		dprt[0] = lpm_get_dst_port_with_ipv4(qconf, pkt[0],
+							dst.u32[0], portid);
+		dprt[1] = lpm_get_dst_port_with_ipv4(qconf, pkt[1],
+							dst.u32[1], portid);
+		dprt[2] = lpm_get_dst_port_with_ipv4(qconf, pkt[2],
+							dst.u32[2], portid);
+		dprt[3] = lpm_get_dst_port_with_ipv4(qconf, pkt[3],
+							dst.u32[3], portid);
+	}
+}
+
+/*
+ * Buffer optimized handling of packets, invoked
+ * from main_loop.
+ */
+static inline void
+l3fwd_lpm_send_packets(int nb_rx, struct rte_mbuf **pkts_burst,
+			uint8_t portid, struct lcore_conf *qconf)
+{
+	int32_t j;
+	uint16_t dst_port[MAX_PKT_BURST];
+	vector unsigned int dip[MAX_PKT_BURST / FWDSTEP];
+	uint32_t ipv4_flag[MAX_PKT_BURST / FWDSTEP];
+	const int32_t k = RTE_ALIGN_FLOOR(nb_rx, FWDSTEP);
+
+	for (j = 0; j != k; j += FWDSTEP)
+		processx4_step1(&pkts_burst[j], &dip[j / FWDSTEP],
+				&ipv4_flag[j / FWDSTEP]);
+
+	for (j = 0; j != k; j += FWDSTEP)
+		processx4_step2(qconf, dip[j / FWDSTEP],
+				ipv4_flag[j / FWDSTEP],
+				portid, &pkts_burst[j], &dst_port[j]);
+
+	/* Classify last up to 3 packets one by one */
+	switch (nb_rx % FWDSTEP) {
+	case 3:
+		dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], portid);
+		j++;
+		/* fall-through */
+	case 2:
+		dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], portid);
+		j++;
+		/* fall-through */
+	case 1:
+		dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], portid);
+		j++;
+		/* fall-through */
+	}
+
+	send_packets_multi(qconf, pkts_burst, dst_port, nb_rx);
+}
+
+#endif /* __L3FWD_LPM_ALTIVEC_H__ */
diff --git a/examples/l3fwd/l3fwd_lpm_neon.h b/examples/l3fwd/l3fwd_lpm_neon.h
index baedbfe8..85f314d1 100644
--- a/examples/l3fwd/l3fwd_lpm_neon.h
+++ b/examples/l3fwd/l3fwd_lpm_neon.h
@@ -82,7 +82,7 @@ static inline void
 processx4_step2(const struct lcore_conf *qconf,
 		int32x4_t dip,
 		uint32_t ipv4_flag,
-		uint8_t portid,
+		uint16_t portid,
 		struct rte_mbuf *pkt[FWDSTEP],
 		uint16_t dprt[FWDSTEP])
 {
@@ -115,7 +115,7 @@ processx4_step2(const struct lcore_conf *qconf,
  */
 static inline void
 l3fwd_lpm_send_packets(int nb_rx, struct rte_mbuf **pkts_burst,
-			uint8_t portid, struct lcore_conf *qconf)
+			uint16_t portid, struct lcore_conf *qconf)
 {
 	int32_t i = 0, j = 0;
 	uint16_t dst_port[MAX_PKT_BURST];
diff --git a/examples/l3fwd/l3fwd_lpm_sse.h b/examples/l3fwd/l3fwd_lpm_sse.h
index 4e294c84..d474396e 100644
--- a/examples/l3fwd/l3fwd_lpm_sse.h
+++ b/examples/l3fwd/l3fwd_lpm_sse.h
@@ -79,7 +79,7 @@ static inline void
 processx4_step2(const struct lcore_conf *qconf,
 		__m128i dip,
 		uint32_t ipv4_flag,
-		uint8_t portid,
+		uint16_t portid,
 		struct rte_mbuf *pkt[FWDSTEP],
 		uint16_t dprt[FWDSTEP])
 {
@@ -112,7 +112,7 @@ processx4_step2(const struct lcore_conf *qconf,
  */
 static inline void
 l3fwd_lpm_send_packets(int nb_rx, struct rte_mbuf **pkts_burst,
-			uint8_t portid, struct lcore_conf *qconf)
+			uint16_t portid, struct lcore_conf *qconf)
 {
 	int32_t j;
 	uint16_t dst_port[MAX_PKT_BURST];
diff --git a/examples/l3fwd/l3fwd_neon.h b/examples/l3fwd/l3fwd_neon.h
index 42d50d3c..b319b5a9 100644
--- a/examples/l3fwd/l3fwd_neon.h
+++ b/examples/l3fwd/l3fwd_neon.h
@@ -114,6 +114,7 @@ port_groupx4(uint16_t pn[FWDSTEP + 1], uint16_t *lp, uint16x8_t dp1,
 
 	/* update last port counter. */
 	lp[0] += gptbl[v].lpv;
+	rte_compiler_barrier();
 
 	/* if dest port value has changed. */
 	if (v != GRPMSK) {
@@ -192,7 +193,7 @@ send_packets_multi(struct lcore_conf *qconf, struct rte_mbuf **pkts_burst,
 			 * dp1:
 			 * <d[j], d[j+1], d[j+2], d[j+3], ... >
 			 */
-			dp1 = vextq_u16(dp1, dp1, FWDSTEP - 1);
+			dp1 = vextq_u16(dp2, dp1, FWDSTEP - 1);
 		}
 
 		/*
diff --git a/examples/l3fwd/main.c b/examples/l3fwd/main.c
index 81995fdb..6229568f 100644
--- a/examples/l3fwd/main.c
+++ b/examples/l3fwd/main.c
@@ -50,7 +50,6 @@
 #include <rte_log.h>
 #include <rte_memory.h>
 #include <rte_memcpy.h>
-#include <rte_memzone.h>
 #include <rte_eal.h>
 #include <rte_launch.h>
 #include <rte_atomic.h>
@@ -60,7 +59,6 @@
 #include <rte_per_lcore.h>
 #include <rte_branch_prediction.h>
 #include <rte_interrupts.h>
-#include <rte_pci.h>
 #include <rte_random.h>
 #include <rte_debug.h>
 #include <rte_ether.h>
@@ -124,7 +122,7 @@ uint32_t hash_entry_number = HASH_ENTRY_NUMBER_DEFAULT;
 struct lcore_conf lcore_conf[RTE_MAX_LCORE];
 
 struct lcore_params {
-	uint8_t port_id;
+	uint16_t port_id;
 	uint8_t queue_id;
 	uint8_t lcore_id;
 } __rte_cache_aligned;
@@ -245,7 +243,7 @@ check_lcore_params(void)
 static int
 check_port_config(const unsigned nb_ports)
 {
-	unsigned portid;
+	uint16_t portid;
 	uint16_t i;
 
 	for (i = 0; i < nb_lcore_params; ++i) {
@@ -263,7 +261,7 @@ check_port_config(const unsigned nb_ports)
 }
 
 static uint8_t
-get_port_n_rx_queues(const uint8_t port)
+get_port_n_rx_queues(const uint16_t port)
 {
 	int queue = -1;
 	uint16_t i;
@@ -445,7 +443,7 @@ parse_config(const char *q_arg)
 static void
 parse_eth_dest(const char *optarg)
 {
-	uint8_t portid;
+	uint16_t portid;
 	char *port_end;
 	uint8_t c, *dest, peer_addr[6];
 
@@ -750,11 +748,12 @@ init_mem(unsigned nb_mbuf)
 
 /* Check the link status of all ports in up to 9s, and print them finally */
 static void
-check_all_ports_link_status(uint8_t port_num, uint32_t port_mask)
+check_all_ports_link_status(uint16_t port_num, uint32_t port_mask)
 {
 #define CHECK_INTERVAL 100 /* 100ms */
 #define MAX_CHECK_TIME 90 /* 9s (90 * 100ms) in total */
-	uint8_t portid, count, all_ports_up, print_flag = 0;
+	uint16_t portid;
+	uint8_t count, all_ports_up, print_flag = 0;
 	struct rte_eth_link link;
 
 	printf("\nChecking link status");
@@ -773,14 +772,13 @@ check_all_ports_link_status(uint8_t port_num, uint32_t port_mask)
 			/* print link status if flag set */
 			if (print_flag == 1) {
 				if (link.link_status)
-					printf("Port %d Link Up - speed %u "
-						"Mbps - %s\n", (uint8_t)portid,
-						(unsigned)link.link_speed,
+					printf(
+					"Port%d Link Up. Speed %u Mbps -%s\n",
+						portid, link.link_speed,
 				(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
 					("full-duplex") : ("half-duplex\n"));
 				else
-					printf("Port %d Link Down\n",
-						(uint8_t)portid);
+					printf("Port %d Link Down\n", portid);
 				continue;
 			}
 			/* clear all_ports_up flag if any link down */
@@ -818,7 +816,7 @@ signal_handler(int signum)
 }
 
 static int
-prepare_ptype_parser(uint8_t portid, uint16_t queueid)
+prepare_ptype_parser(uint16_t portid, uint16_t queueid)
 {
 	if (parse_ptype) {
 		printf("Port %d: softly parse packet type info\n", portid);
@@ -847,10 +845,10 @@ main(int argc, char **argv)
 	struct rte_eth_txconf *txconf;
 	int ret;
 	unsigned nb_ports;
-	uint16_t queueid;
+	uint16_t queueid, portid;
 	unsigned lcore_id;
 	uint32_t n_tx_queue, nb_lcores;
-	uint8_t portid, nb_rx_queue, queue, socketid;
+	uint8_t nb_rx_queue, queue, socketid;
 
 	/* init EAL */
 	ret = rte_eal_init(argc, argv);
@@ -1048,7 +1046,7 @@ main(int argc, char **argv)
 	}
 
 
-	check_all_ports_link_status((uint8_t)nb_ports, enabled_port_mask);
+	check_all_ports_link_status(nb_ports, enabled_port_mask);
 
 	ret = 0;
 	/* launch per-lcore init on every lcore */