Imported Upstream version 16.11

Change-Id: I1944c65ddc88a9ad70f8c0eb6731552b84fbcb77
Signed-off-by: Christian Ehrhardt <christian.ehrhardt@canonical.com>

14 files changed, 973 insertions, 292 deletions

diff --git a/app/test-pmd/Makefile b/app/test-pmd/Makefile
index 2a0b5a5d..891b85ac 100644
--- a/app/test-pmd/Makefile
+++ b/app/test-pmd/Makefile
@@ -58,6 +58,8 @@ SRCS-y += csumonly.c
 SRCS-y += icmpecho.c
 SRCS-$(CONFIG_RTE_LIBRTE_IEEE1588) += ieee1588fwd.c
 
+_LDLIBS-$(CONFIG_RTE_LIBRTE_IXGBE_PMD) += -lrte_pmd_ixgbe
+
 CFLAGS_cmdline.o := -D_GNU_SOURCE
 
 # this application needs libraries first
diff --git a/app/test-pmd/cmdline.c b/app/test-pmd/cmdline.c
index 09a28327..63b55dcb 100644
--- a/app/test-pmd/cmdline.c
+++ b/app/test-pmd/cmdline.c
@@ -87,7 +87,9 @@
 #ifdef RTE_LIBRTE_PMD_BOND
 #include <rte_eth_bond.h>
 #endif
-
+#ifdef RTE_LIBRTE_IXGBE_PMD
+#include <rte_pmd_ixgbe.h>
+#endif
 #include "testpmd.h"
 
 static struct cmdline *testpmd_cl;
@@ -260,12 +262,37 @@ static void cmd_help_long_parsed(void *parsed_result,
 			"set portlist (x[,y]*)\n"
 			"    Set the list of forwarding ports.\n\n"
 
+#ifdef RTE_LIBRTE_IXGBE_PMD
+			"set tx loopback (port_id) (on|off)\n"
+			"    Enable or disable tx loopback.\n\n"
+
+			"set all queues drop (port_id) (on|off)\n"
+			"    Set drop enable bit for all queues.\n\n"
+
+			"set vf split drop (port_id) (vf_id) (on|off)\n"
+			"    Set split drop enable bit for a VF from the PF.\n\n"
+
+			"set vf mac antispoof (port_id) (vf_id) (on|off).\n"
+			"    Set MAC antispoof for a VF from the PF.\n\n"
+#endif
+
 			"vlan set strip (on|off) (port_id)\n"
 			"    Set the VLAN strip on a port.\n\n"
 
 			"vlan set stripq (on|off) (port_id,queue_id)\n"
 			"    Set the VLAN strip for a queue on a port.\n\n"
 
+#ifdef RTE_LIBRTE_IXGBE_PMD
+			"set vf vlan stripq (port_id) (vf_id) (on|off)\n"
+			"    Set the VLAN strip for all queues in a pool for a VF from the PF.\n\n"
+
+			"set vf vlan insert (port_id) (vf_id) (vlan_id)\n"
+			"    Set VLAN insert for a VF from the PF.\n\n"
+
+			"set vf vlan antispoof (port_id) (vf_id) (on|off)\n"
+			"    Set VLAN antispoof for a VF from the PF.\n\n"
+#endif
+
 			"vlan set filter (on|off) (port_id)\n"
 			"    Set the VLAN filter on a port.\n\n"
 
@@ -359,6 +386,11 @@ static void cmd_help_long_parsed(void *parsed_result,
 			"mac_addr add port (port_id) vf (vf_id) (mac_address)\n"
 			"    Add a MAC address for a VF on the port.\n\n"
 
+#ifdef RTE_LIBRTE_IXGBE_PMD
+			"set vf mac addr (port_id) (vf_id) (XX:XX:XX:XX:XX:XX)\n"
+			"    Set the MAC address for a VF from the PF.\n\n"
+#endif
+
 			"set port (port_id) uta (mac_address|all) (on|off)\n"
 			"    Add/Remove a or all unicast hash filter(s)"
 			"from port X.\n\n"
@@ -545,7 +577,7 @@ static void cmd_help_long_parsed(void *parsed_result,
 			"    Detach physical or virtual dev by port_id\n\n"
 
 			"port config (port_id|all)"
-			" speed (10|100|1000|10000|40000|100000|auto)"
+			" speed (10|100|1000|10000|25000|40000|50000|100000|auto)"
 			" duplex (half|full|auto)\n"
 			"    Set speed and duplex for all ports or port_id\n\n"
 
@@ -1016,8 +1048,12 @@ parse_and_check_speed_duplex(char *speedstr, char *duplexstr, uint32_t *speed)
 			*speed = ETH_LINK_SPEED_1G;
 		} else if (!strcmp(speedstr, "10000")) {
 			*speed = ETH_LINK_SPEED_10G;
+		} else if (!strcmp(speedstr, "25000")) {
+			*speed = ETH_LINK_SPEED_25G;
 		} else if (!strcmp(speedstr, "40000")) {
 			*speed = ETH_LINK_SPEED_40G;
+		} else if (!strcmp(speedstr, "50000")) {
+			*speed = ETH_LINK_SPEED_50G;
 		} else if (!strcmp(speedstr, "100000")) {
 			*speed = ETH_LINK_SPEED_100G;
 		} else if (!strcmp(speedstr, "auto")) {
@@ -1067,7 +1103,7 @@ cmdline_parse_token_string_t cmd_config_speed_all_item1 =
 	TOKEN_STRING_INITIALIZER(struct cmd_config_speed_all, item1, "speed");
 cmdline_parse_token_string_t cmd_config_speed_all_value1 =
 	TOKEN_STRING_INITIALIZER(struct cmd_config_speed_all, value1,
-						"10#100#1000#10000#40000#100000#auto");
+				"10#100#1000#10000#25000#40000#50000#100000#auto");
 cmdline_parse_token_string_t cmd_config_speed_all_item2 =
 	TOKEN_STRING_INITIALIZER(struct cmd_config_speed_all, item2, "duplex");
 cmdline_parse_token_string_t cmd_config_speed_all_value2 =
@@ -1077,7 +1113,8 @@ cmdline_parse_token_string_t cmd_config_speed_all_value2 =
 cmdline_parse_inst_t cmd_config_speed_all = {
 	.f = cmd_config_speed_all_parsed,
 	.data = NULL,
-	.help_str = "port config all speed 10|100|1000|10000|40000|100000|auto duplex "
+	.help_str = "port config all speed "
+		"10|100|1000|10000|25000|40000|50000|100000|auto duplex "
 							"half|full|auto",
 	.tokens = {
 		(void *)&cmd_config_speed_all_port,
@@ -1141,7 +1178,7 @@ cmdline_parse_token_string_t cmd_config_speed_specific_item1 =
 								"speed");
 cmdline_parse_token_string_t cmd_config_speed_specific_value1 =
 	TOKEN_STRING_INITIALIZER(struct cmd_config_speed_specific, value1,
-						"10#100#1000#10000#40000#100000#auto");
+				"10#100#1000#10000#25000#40000#50000#100000#auto");
 cmdline_parse_token_string_t cmd_config_speed_specific_item2 =
 	TOKEN_STRING_INITIALIZER(struct cmd_config_speed_specific, item2,
 								"duplex");
@@ -1152,7 +1189,8 @@ cmdline_parse_token_string_t cmd_config_speed_specific_value2 =
 cmdline_parse_inst_t cmd_config_speed_specific = {
 	.f = cmd_config_speed_specific_parsed,
 	.data = NULL,
-	.help_str = "port config X speed 10|100|1000|10000|40000|100000|auto duplex "
+	.help_str = "port config X speed "
+		"10|100|1000|10000|25000|40000|50000|100000|auto duplex "
 							"half|full|auto",
 	.tokens = {
 		(void *)&cmd_config_speed_specific_port,
@@ -3485,7 +3523,7 @@ cmdline_parse_inst_t cmd_csum_tunnel = {
 	},
 };
 
-/* *** ENABLE HARDWARE SEGMENTATION IN TX PACKETS *** */
+/* *** ENABLE HARDWARE SEGMENTATION IN TX NON-TUNNELED PACKETS *** */
 struct cmd_tso_set_result {
 	cmdline_fixed_string_t tso;
 	cmdline_fixed_string_t mode;
@@ -3508,9 +3546,9 @@ cmd_tso_set_parsed(void *parsed_result,
 		ports[res->port_id].tso_segsz = res->tso_segsz;
 
 	if (ports[res->port_id].tso_segsz == 0)
-		printf("TSO is disabled\n");
+		printf("TSO for non-tunneled packets is disabled\n");
 	else
-		printf("TSO segment size is %d\n",
+		printf("TSO segment size for non-tunneled packets is %d\n",
 			ports[res->port_id].tso_segsz);
 
 	/* display warnings if configuration is not supported by the NIC */
@@ -3538,8 +3576,8 @@ cmdline_parse_token_num_t cmd_tso_set_portid =
 cmdline_parse_inst_t cmd_tso_set = {
 	.f = cmd_tso_set_parsed,
 	.data = NULL,
-	.help_str = "Set TSO segment size for csum engine (0 to disable): "
-	"tso set <tso_segsz> <port>",
+	.help_str = "Set TSO segment size of non-tunneled packets "
+	"for csum engine (0 to disable): tso set <tso_segsz> <port>",
 	.tokens = {
 		(void *)&cmd_tso_set_tso,
 		(void *)&cmd_tso_set_mode,
@@ -3557,8 +3595,8 @@ cmdline_parse_token_string_t cmd_tso_show_mode =
 cmdline_parse_inst_t cmd_tso_show = {
 	.f = cmd_tso_set_parsed,
 	.data = NULL,
-	.help_str = "Show TSO segment size for csum engine: "
-	"tso show <port>",
+	.help_str = "Show TSO segment size of non-tunneled packets "
+	"for csum engine: tso show <port>",
 	.tokens = {
 		(void *)&cmd_tso_set_tso,
 		(void *)&cmd_tso_show_mode,
@@ -3567,6 +3605,122 @@ cmdline_parse_inst_t cmd_tso_show = {
 	},
 };
 
+/* *** ENABLE HARDWARE SEGMENTATION IN TX TUNNELED PACKETS *** */
+struct cmd_tunnel_tso_set_result {
+	cmdline_fixed_string_t tso;
+	cmdline_fixed_string_t mode;
+	uint16_t tso_segsz;
+	uint8_t port_id;
+};
+
+static void
+check_tunnel_tso_nic_support(uint8_t port_id)
+{
+	struct rte_eth_dev_info dev_info;
+
+	rte_eth_dev_info_get(port_id, &dev_info);
+	if (!(dev_info.tx_offload_capa & DEV_TX_OFFLOAD_VXLAN_TNL_TSO))
+		printf("Warning: TSO enabled but VXLAN TUNNEL TSO not "
+		       "supported by port %d\n", port_id);
+	if (!(dev_info.tx_offload_capa & DEV_TX_OFFLOAD_GRE_TNL_TSO))
+		printf("Warning: TSO enabled but GRE TUNNEL TSO not "
+			"supported by port %d\n", port_id);
+	if (!(dev_info.tx_offload_capa & DEV_TX_OFFLOAD_IPIP_TNL_TSO))
+		printf("Warning: TSO enabled but IPIP TUNNEL TSO not "
+		       "supported by port %d\n", port_id);
+	if (!(dev_info.tx_offload_capa & DEV_TX_OFFLOAD_GENEVE_TNL_TSO))
+		printf("Warning: TSO enabled but GENEVE TUNNEL TSO not "
+		       "supported by port %d\n", port_id);
+}
+
+static void
+cmd_tunnel_tso_set_parsed(void *parsed_result,
+			  __attribute__((unused)) struct cmdline *cl,
+			  __attribute__((unused)) void *data)
+{
+	struct cmd_tunnel_tso_set_result *res = parsed_result;
+
+	if (port_id_is_invalid(res->port_id, ENABLED_WARN))
+		return;
+
+	if (!strcmp(res->mode, "set"))
+		ports[res->port_id].tunnel_tso_segsz = res->tso_segsz;
+
+	if (ports[res->port_id].tunnel_tso_segsz == 0)
+		printf("TSO for tunneled packets is disabled\n");
+	else {
+		printf("TSO segment size for tunneled packets is %d\n",
+			ports[res->port_id].tunnel_tso_segsz);
+
+		/* Below conditions are needed to make it work:
+		 * (1) tunnel TSO is supported by the NIC;
+		 * (2) "csum parse_tunnel" must be set so that tunneled pkts
+		 * are recognized;
+		 * (3) for tunneled pkts with outer L3 of IPv4,
+		 * "csum set outer-ip" must be set to hw, because after tso,
+		 * total_len of outer IP header is changed, and the checksum
+		 * of outer IP header calculated by sw should be wrong; that
+		 * is not necessary for IPv6 tunneled pkts because there's no
+		 * checksum in IP header anymore.
+		 */
+		check_tunnel_tso_nic_support(res->port_id);
+
+		if (!(ports[res->port_id].tx_ol_flags &
+		      TESTPMD_TX_OFFLOAD_PARSE_TUNNEL))
+			printf("Warning: csum parse_tunnel must be set "
+				"so that tunneled packets are recognized\n");
+		if (!(ports[res->port_id].tx_ol_flags &
+		      TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM))
+			printf("Warning: csum set outer-ip must be set to hw "
+				"if outer L3 is IPv4; not necessary for IPv6\n");
+	}
+}
+
+cmdline_parse_token_string_t cmd_tunnel_tso_set_tso =
+	TOKEN_STRING_INITIALIZER(struct cmd_tunnel_tso_set_result,
+				tso, "tunnel_tso");
+cmdline_parse_token_string_t cmd_tunnel_tso_set_mode =
+	TOKEN_STRING_INITIALIZER(struct cmd_tunnel_tso_set_result,
+				mode, "set");
+cmdline_parse_token_num_t cmd_tunnel_tso_set_tso_segsz =
+	TOKEN_NUM_INITIALIZER(struct cmd_tunnel_tso_set_result,
+				tso_segsz, UINT16);
+cmdline_parse_token_num_t cmd_tunnel_tso_set_portid =
+	TOKEN_NUM_INITIALIZER(struct cmd_tunnel_tso_set_result,
+				port_id, UINT8);
+
+cmdline_parse_inst_t cmd_tunnel_tso_set = {
+	.f = cmd_tunnel_tso_set_parsed,
+	.data = NULL,
+	.help_str = "Set TSO segment size of tunneled packets for csum engine "
+	"(0 to disable): tunnel_tso set <tso_segsz> <port>",
+	.tokens = {
+		(void *)&cmd_tunnel_tso_set_tso,
+		(void *)&cmd_tunnel_tso_set_mode,
+		(void *)&cmd_tunnel_tso_set_tso_segsz,
+		(void *)&cmd_tunnel_tso_set_portid,
+		NULL,
+	},
+};
+
+cmdline_parse_token_string_t cmd_tunnel_tso_show_mode =
+	TOKEN_STRING_INITIALIZER(struct cmd_tunnel_tso_set_result,
+				mode, "show");
+
+
+cmdline_parse_inst_t cmd_tunnel_tso_show = {
+	.f = cmd_tunnel_tso_set_parsed,
+	.data = NULL,
+	.help_str = "Show TSO segment size of tunneled packets "
+	"for csum engine: tunnel_tso show <port>",
+	.tokens = {
+		(void *)&cmd_tunnel_tso_set_tso,
+		(void *)&cmd_tunnel_tso_show_mode,
+		(void *)&cmd_tunnel_tso_set_portid,
+		NULL,
+	},
+};
+
 /* *** ENABLE/DISABLE FLUSH ON RX STREAMS *** */
 struct cmd_set_flush_rx {
 	cmdline_fixed_string_t set;
@@ -4404,7 +4558,7 @@ static void cmd_create_bonded_device_parsed(void *parsed_result,
 		return;
 	}
 
-	snprintf(ethdev_name, RTE_ETH_NAME_MAX_LEN, "eth_bond_testpmd_%d",
+	snprintf(ethdev_name, RTE_ETH_NAME_MAX_LEN, "net_bond_testpmd_%d",
 			bond_dev_num++);
 
 	/* Create a new bonded device. */
@@ -10598,6 +10752,664 @@ cmdline_parse_inst_t cmd_config_e_tag_filter_del = {
 		NULL,
 	},
 };
+#ifdef RTE_LIBRTE_IXGBE_PMD
+
+/* vf vlan anti spoof configuration */
+
+/* Common result structure for vf vlan anti spoof */
+struct cmd_vf_vlan_anti_spoof_result {
+	cmdline_fixed_string_t set;
+	cmdline_fixed_string_t vf;
+	cmdline_fixed_string_t vlan;
+	cmdline_fixed_string_t antispoof;
+	uint8_t port_id;
+	uint32_t vf_id;
+	cmdline_fixed_string_t on_off;
+};
+
+/* Common CLI fields for vf vlan anti spoof enable disable */
+cmdline_parse_token_string_t cmd_vf_vlan_anti_spoof_set =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_vlan_anti_spoof_result,
+		 set, "set");
+cmdline_parse_token_string_t cmd_vf_vlan_anti_spoof_vf =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_vlan_anti_spoof_result,
+		 vf, "vf");
+cmdline_parse_token_string_t cmd_vf_vlan_anti_spoof_vlan =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_vlan_anti_spoof_result,
+		 vlan, "vlan");
+cmdline_parse_token_string_t cmd_vf_vlan_anti_spoof_antispoof =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_vlan_anti_spoof_result,
+		 antispoof, "antispoof");
+cmdline_parse_token_num_t cmd_vf_vlan_anti_spoof_port_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_vf_vlan_anti_spoof_result,
+		 port_id, UINT8);
+cmdline_parse_token_num_t cmd_vf_vlan_anti_spoof_vf_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_vf_vlan_anti_spoof_result,
+		 vf_id, UINT32);
+cmdline_parse_token_string_t cmd_vf_vlan_anti_spoof_on_off =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_vlan_anti_spoof_result,
+		 on_off, "on#off");
+
+static void
+cmd_set_vf_vlan_anti_spoof_parsed(
+	void *parsed_result,
+	__attribute__((unused)) struct cmdline *cl,
+	__attribute__((unused)) void *data)
+{
+	struct cmd_vf_vlan_anti_spoof_result *res = parsed_result;
+	int ret = 0;
+	int is_on = (strcmp(res->on_off, "on") == 0) ? 1 : 0;
+
+	ret = rte_pmd_ixgbe_set_vf_vlan_anti_spoof(res->port_id, res->vf_id,
+			is_on);
+	switch (ret) {
+	case 0:
+		break;
+	case -EINVAL:
+		printf("invalid vf_id %d\n", res->vf_id);
+		break;
+	case -ENODEV:
+		printf("invalid port_id %d\n", res->port_id);
+		break;
+	default:
+		printf("programming error: (%s)\n", strerror(-ret));
+	}
+}
+
+cmdline_parse_inst_t cmd_set_vf_vlan_anti_spoof = {
+	.f = cmd_set_vf_vlan_anti_spoof_parsed,
+	.data = NULL,
+	.help_str = "set vf vlan antispoof port_id vf_id on|off",
+	.tokens = {
+		(void *)&cmd_vf_vlan_anti_spoof_set,
+		(void *)&cmd_vf_vlan_anti_spoof_vf,
+		(void *)&cmd_vf_vlan_anti_spoof_vlan,
+		(void *)&cmd_vf_vlan_anti_spoof_antispoof,
+		(void *)&cmd_vf_vlan_anti_spoof_port_id,
+		(void *)&cmd_vf_vlan_anti_spoof_vf_id,
+		(void *)&cmd_vf_vlan_anti_spoof_on_off,
+		NULL,
+	},
+};
+
+/* vf mac anti spoof configuration */
+
+/* Common result structure for vf mac anti spoof */
+struct cmd_vf_mac_anti_spoof_result {
+	cmdline_fixed_string_t set;
+	cmdline_fixed_string_t vf;
+	cmdline_fixed_string_t mac;
+	cmdline_fixed_string_t antispoof;
+	uint8_t port_id;
+	uint32_t vf_id;
+	cmdline_fixed_string_t on_off;
+};
+
+/* Common CLI fields for vf mac anti spoof enable disable */
+cmdline_parse_token_string_t cmd_vf_mac_anti_spoof_set =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_mac_anti_spoof_result,
+		 set, "set");
+cmdline_parse_token_string_t cmd_vf_mac_anti_spoof_vf =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_mac_anti_spoof_result,
+		 vf, "vf");
+cmdline_parse_token_string_t cmd_vf_mac_anti_spoof_mac =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_mac_anti_spoof_result,
+		 mac, "mac");
+cmdline_parse_token_string_t cmd_vf_mac_anti_spoof_antispoof =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_mac_anti_spoof_result,
+		 antispoof, "antispoof");
+cmdline_parse_token_num_t cmd_vf_mac_anti_spoof_port_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_vf_mac_anti_spoof_result,
+		 port_id, UINT8);
+cmdline_parse_token_num_t cmd_vf_mac_anti_spoof_vf_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_vf_mac_anti_spoof_result,
+		 vf_id, UINT32);
+cmdline_parse_token_string_t cmd_vf_mac_anti_spoof_on_off =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_mac_anti_spoof_result,
+		 on_off, "on#off");
+
+static void
+cmd_set_vf_mac_anti_spoof_parsed(
+	void *parsed_result,
+	__attribute__((unused)) struct cmdline *cl,
+	__attribute__((unused)) void *data)
+{
+	struct cmd_vf_mac_anti_spoof_result *res = parsed_result;
+	int ret;
+	int is_on = (strcmp(res->on_off, "on") == 0) ? 1 : 0;
+
+	ret = rte_pmd_ixgbe_set_vf_mac_anti_spoof(res->port_id, res->vf_id,
+			is_on);
+	switch (ret) {
+	case 0:
+		break;
+	case -EINVAL:
+		printf("invalid vf_id %d or is_on %d\n", res->vf_id, is_on);
+		break;
+	case -ENODEV:
+		printf("invalid port_id %d\n", res->port_id);
+		break;
+	default:
+		printf("programming error: (%s)\n", strerror(-ret));
+	}
+}
+
+cmdline_parse_inst_t cmd_set_vf_mac_anti_spoof = {
+	.f = cmd_set_vf_mac_anti_spoof_parsed,
+	.data = NULL,
+	.help_str = "set vf mac antispoof port_id vf_id on|off",
+	.tokens = {
+		(void *)&cmd_vf_mac_anti_spoof_set,
+		(void *)&cmd_vf_mac_anti_spoof_vf,
+		(void *)&cmd_vf_mac_anti_spoof_mac,
+		(void *)&cmd_vf_mac_anti_spoof_antispoof,
+		(void *)&cmd_vf_mac_anti_spoof_port_id,
+		(void *)&cmd_vf_mac_anti_spoof_vf_id,
+		(void *)&cmd_vf_mac_anti_spoof_on_off,
+		NULL,
+	},
+};
+
+/* vf vlan strip queue configuration */
+
+/* Common result structure for vf mac anti spoof */
+struct cmd_vf_vlan_stripq_result {
+	cmdline_fixed_string_t set;
+	cmdline_fixed_string_t vf;
+	cmdline_fixed_string_t vlan;
+	cmdline_fixed_string_t stripq;
+	uint8_t port_id;
+	uint16_t vf_id;
+	cmdline_fixed_string_t on_off;
+};
+
+/* Common CLI fields for vf vlan strip enable disable */
+cmdline_parse_token_string_t cmd_vf_vlan_stripq_set =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_vlan_stripq_result,
+		 set, "set");
+cmdline_parse_token_string_t cmd_vf_vlan_stripq_vf =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_vlan_stripq_result,
+		 vf, "vf");
+cmdline_parse_token_string_t cmd_vf_vlan_stripq_vlan =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_vlan_stripq_result,
+		 vlan, "vlan");
+cmdline_parse_token_string_t cmd_vf_vlan_stripq_stripq =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_vlan_stripq_result,
+		 stripq, "stripq");
+cmdline_parse_token_num_t cmd_vf_vlan_stripq_port_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_vf_vlan_stripq_result,
+		 port_id, UINT8);
+cmdline_parse_token_num_t cmd_vf_vlan_stripq_vf_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_vf_vlan_stripq_result,
+		 vf_id, UINT16);
+cmdline_parse_token_string_t cmd_vf_vlan_stripq_on_off =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_vlan_stripq_result,
+		 on_off, "on#off");
+
+static void
+cmd_set_vf_vlan_stripq_parsed(
+	void *parsed_result,
+	__attribute__((unused)) struct cmdline *cl,
+	__attribute__((unused)) void *data)
+{
+	struct cmd_vf_vlan_stripq_result *res = parsed_result;
+	int ret = 0;
+	int is_on = (strcmp(res->on_off, "on") == 0) ? 1 : 0;
+
+	ret = rte_pmd_ixgbe_set_vf_vlan_stripq(res->port_id, res->vf_id, is_on);
+	switch (ret) {
+	case 0:
+		break;
+	case -EINVAL:
+		printf("invalid vf_id %d or is_on %d\n", res->vf_id, is_on);
+		break;
+	case -ENODEV:
+		printf("invalid port_id %d\n", res->port_id);
+		break;
+	default:
+		printf("programming error: (%s)\n", strerror(-ret));
+	}
+}
+
+cmdline_parse_inst_t cmd_set_vf_vlan_stripq = {
+	.f = cmd_set_vf_vlan_stripq_parsed,
+	.data = NULL,
+	.help_str = "set vf vlan stripq port_id vf_id on|off",
+	.tokens = {
+		(void *)&cmd_vf_vlan_stripq_set,
+		(void *)&cmd_vf_vlan_stripq_vf,
+		(void *)&cmd_vf_vlan_stripq_vlan,
+		(void *)&cmd_vf_vlan_stripq_stripq,
+		(void *)&cmd_vf_vlan_stripq_port_id,
+		(void *)&cmd_vf_vlan_stripq_vf_id,
+		(void *)&cmd_vf_vlan_stripq_on_off,
+		NULL,
+	},
+};
+
+/* vf vlan insert configuration */
+
+/* Common result structure for vf vlan insert */
+struct cmd_vf_vlan_insert_result {
+	cmdline_fixed_string_t set;
+	cmdline_fixed_string_t vf;
+	cmdline_fixed_string_t vlan;
+	cmdline_fixed_string_t insert;
+	uint8_t port_id;
+	uint16_t vf_id;
+	uint16_t vlan_id;
+};
+
+/* Common CLI fields for vf vlan insert enable disable */
+cmdline_parse_token_string_t cmd_vf_vlan_insert_set =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_vlan_insert_result,
+		 set, "set");
+cmdline_parse_token_string_t cmd_vf_vlan_insert_vf =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_vlan_insert_result,
+		 vf, "vf");
+cmdline_parse_token_string_t cmd_vf_vlan_insert_vlan =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_vlan_insert_result,
+		 vlan, "vlan");
+cmdline_parse_token_string_t cmd_vf_vlan_insert_insert =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_vlan_insert_result,
+		 insert, "insert");
+cmdline_parse_token_num_t cmd_vf_vlan_insert_port_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_vf_vlan_insert_result,
+		 port_id, UINT8);
+cmdline_parse_token_num_t cmd_vf_vlan_insert_vf_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_vf_vlan_insert_result,
+		 vf_id, UINT16);
+cmdline_parse_token_num_t cmd_vf_vlan_insert_vlan_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_vf_vlan_insert_result,
+		 vlan_id, UINT16);
+
+static void
+cmd_set_vf_vlan_insert_parsed(
+	void *parsed_result,
+	__attribute__((unused)) struct cmdline *cl,
+	__attribute__((unused)) void *data)
+{
+	struct cmd_vf_vlan_insert_result *res = parsed_result;
+	int ret;
+
+	ret = rte_pmd_ixgbe_set_vf_vlan_insert(res->port_id, res->vf_id, res->vlan_id);
+	switch (ret) {
+	case 0:
+		break;
+	case -EINVAL:
+		printf("invalid vf_id %d or vlan_id %d\n", res->vf_id, res->vlan_id);
+		break;
+	case -ENODEV:
+		printf("invalid port_id %d\n", res->port_id);
+		break;
+	default:
+		printf("programming error: (%s)\n", strerror(-ret));
+	}
+}
+
+cmdline_parse_inst_t cmd_set_vf_vlan_insert = {
+	.f = cmd_set_vf_vlan_insert_parsed,
+	.data = NULL,
+	.help_str = "set vf vlan insert port_id vf_id vlan_id",
+	.tokens = {
+		(void *)&cmd_vf_vlan_insert_set,
+		(void *)&cmd_vf_vlan_insert_vf,
+		(void *)&cmd_vf_vlan_insert_vlan,
+		(void *)&cmd_vf_vlan_insert_insert,
+		(void *)&cmd_vf_vlan_insert_port_id,
+		(void *)&cmd_vf_vlan_insert_vf_id,
+		(void *)&cmd_vf_vlan_insert_vlan_id,
+		NULL,
+	},
+};
+
+/* tx loopback configuration */
+
+/* Common result structure for tx loopback */
+struct cmd_tx_loopback_result {
+	cmdline_fixed_string_t set;
+	cmdline_fixed_string_t tx;
+	cmdline_fixed_string_t loopback;
+	uint8_t port_id;
+	cmdline_fixed_string_t on_off;
+};
+
+/* Common CLI fields for tx loopback enable disable */
+cmdline_parse_token_string_t cmd_tx_loopback_set =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_tx_loopback_result,
+		 set, "set");
+cmdline_parse_token_string_t cmd_tx_loopback_tx =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_tx_loopback_result,
+		 tx, "tx");
+cmdline_parse_token_string_t cmd_tx_loopback_loopback =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_tx_loopback_result,
+		 loopback, "loopback");
+cmdline_parse_token_num_t cmd_tx_loopback_port_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_tx_loopback_result,
+		 port_id, UINT8);
+cmdline_parse_token_string_t cmd_tx_loopback_on_off =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_tx_loopback_result,
+		 on_off, "on#off");
+
+static void
+cmd_set_tx_loopback_parsed(
+	void *parsed_result,
+	__attribute__((unused)) struct cmdline *cl,
+	__attribute__((unused)) void *data)
+{
+	struct cmd_tx_loopback_result *res = parsed_result;
+	int ret;
+	int is_on = (strcmp(res->on_off, "on") == 0) ? 1 : 0;
+
+	ret = rte_pmd_ixgbe_set_tx_loopback(res->port_id, is_on);
+	switch (ret) {
+	case 0:
+		break;
+	case -EINVAL:
+		printf("invalid is_on %d\n", is_on);
+		break;
+	case -ENODEV:
+		printf("invalid port_id %d\n", res->port_id);
+		break;
+	default:
+		printf("programming error: (%s)\n", strerror(-ret));
+	}
+}
+
+cmdline_parse_inst_t cmd_set_tx_loopback = {
+	.f = cmd_set_tx_loopback_parsed,
+	.data = NULL,
+	.help_str = "set tx loopback port_id on|off",
+	.tokens = {
+		(void *)&cmd_tx_loopback_set,
+		(void *)&cmd_tx_loopback_tx,
+		(void *)&cmd_tx_loopback_loopback,
+		(void *)&cmd_tx_loopback_port_id,
+		(void *)&cmd_tx_loopback_on_off,
+		NULL,
+	},
+};
+
+/* all queues drop enable configuration */
+
+/* Common result structure for all queues drop enable */
+struct cmd_all_queues_drop_en_result {
+	cmdline_fixed_string_t set;
+	cmdline_fixed_string_t all;
+	cmdline_fixed_string_t queues;
+	cmdline_fixed_string_t drop;
+	uint8_t port_id;
+	cmdline_fixed_string_t on_off;
+};
+
+/* Common CLI fields for tx loopback enable disable */
+cmdline_parse_token_string_t cmd_all_queues_drop_en_set =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_all_queues_drop_en_result,
+		 set, "set");
+cmdline_parse_token_string_t cmd_all_queues_drop_en_all =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_all_queues_drop_en_result,
+		 all, "all");
+cmdline_parse_token_string_t cmd_all_queues_drop_en_queues =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_all_queues_drop_en_result,
+		 queues, "queues");
+cmdline_parse_token_string_t cmd_all_queues_drop_en_drop =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_all_queues_drop_en_result,
+		 drop, "drop");
+cmdline_parse_token_num_t cmd_all_queues_drop_en_port_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_all_queues_drop_en_result,
+		 port_id, UINT8);
+cmdline_parse_token_string_t cmd_all_queues_drop_en_on_off =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_all_queues_drop_en_result,
+		 on_off, "on#off");
+
+static void
+cmd_set_all_queues_drop_en_parsed(
+	void *parsed_result,
+	__attribute__((unused)) struct cmdline *cl,
+	__attribute__((unused)) void *data)
+{
+	struct cmd_all_queues_drop_en_result *res = parsed_result;
+	int ret = 0;
+	int is_on = (strcmp(res->on_off, "on") == 0) ? 1 : 0;
+
+	ret = rte_pmd_ixgbe_set_all_queues_drop_en(res->port_id, is_on);
+	switch (ret) {
+	case 0:
+		break;
+	case -EINVAL:
+		printf("invalid is_on %d\n", is_on);
+		break;
+	case -ENODEV:
+		printf("invalid port_id %d\n", res->port_id);
+		break;
+	default:
+		printf("programming error: (%s)\n", strerror(-ret));
+	}
+}
+
+cmdline_parse_inst_t cmd_set_all_queues_drop_en = {
+	.f = cmd_set_all_queues_drop_en_parsed,
+	.data = NULL,
+	.help_str = "set all queues drop port_id on|off",
+	.tokens = {
+		(void *)&cmd_all_queues_drop_en_set,
+		(void *)&cmd_all_queues_drop_en_all,
+		(void *)&cmd_all_queues_drop_en_queues,
+		(void *)&cmd_all_queues_drop_en_drop,
+		(void *)&cmd_all_queues_drop_en_port_id,
+		(void *)&cmd_all_queues_drop_en_on_off,
+		NULL,
+	},
+};
+
+/* vf split drop enable configuration */
+
+/* Common result structure for vf split drop enable */
+struct cmd_vf_split_drop_en_result {
+	cmdline_fixed_string_t set;
+	cmdline_fixed_string_t vf;
+	cmdline_fixed_string_t split;
+	cmdline_fixed_string_t drop;
+	uint8_t port_id;
+	uint16_t vf_id;
+	cmdline_fixed_string_t on_off;
+};
+
+/* Common CLI fields for vf split drop enable disable */
+cmdline_parse_token_string_t cmd_vf_split_drop_en_set =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_split_drop_en_result,
+		 set, "set");
+cmdline_parse_token_string_t cmd_vf_split_drop_en_vf =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_split_drop_en_result,
+		 vf, "vf");
+cmdline_parse_token_string_t cmd_vf_split_drop_en_split =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_split_drop_en_result,
+		 split, "split");
+cmdline_parse_token_string_t cmd_vf_split_drop_en_drop =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_split_drop_en_result,
+		 drop, "drop");
+cmdline_parse_token_num_t cmd_vf_split_drop_en_port_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_vf_split_drop_en_result,
+		 port_id, UINT8);
+cmdline_parse_token_num_t cmd_vf_split_drop_en_vf_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_vf_split_drop_en_result,
+		 vf_id, UINT16);
+cmdline_parse_token_string_t cmd_vf_split_drop_en_on_off =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_vf_split_drop_en_result,
+		 on_off, "on#off");
+
+static void
+cmd_set_vf_split_drop_en_parsed(
+	void *parsed_result,
+	__attribute__((unused)) struct cmdline *cl,
+	__attribute__((unused)) void *data)
+{
+	struct cmd_vf_split_drop_en_result *res = parsed_result;
+	int ret;
+	int is_on = (strcmp(res->on_off, "on") == 0) ? 1 : 0;
+
+	ret = rte_pmd_ixgbe_set_vf_split_drop_en(res->port_id, res->vf_id,
+			is_on);
+	switch (ret) {
+	case 0:
+		break;
+	case -EINVAL:
+		printf("invalid vf_id %d or is_on %d\n", res->vf_id, is_on);
+		break;
+	case -ENODEV:
+		printf("invalid port_id %d\n", res->port_id);
+		break;
+	default:
+		printf("programming error: (%s)\n", strerror(-ret));
+	}
+}
+
+cmdline_parse_inst_t cmd_set_vf_split_drop_en = {
+	.f = cmd_set_vf_split_drop_en_parsed,
+	.data = NULL,
+	.help_str = "set vf split drop port_id vf_id on|off",
+	.tokens = {
+		(void *)&cmd_vf_split_drop_en_set,
+		(void *)&cmd_vf_split_drop_en_vf,
+		(void *)&cmd_vf_split_drop_en_split,
+		(void *)&cmd_vf_split_drop_en_drop,
+		(void *)&cmd_vf_split_drop_en_port_id,
+		(void *)&cmd_vf_split_drop_en_vf_id,
+		(void *)&cmd_vf_split_drop_en_on_off,
+		NULL,
+	},
+};
+
+/* vf mac address configuration */
+
+/* Common result structure for vf mac address */
+struct cmd_set_vf_mac_addr_result {
+	cmdline_fixed_string_t set;
+	cmdline_fixed_string_t vf;
+	cmdline_fixed_string_t mac;
+	cmdline_fixed_string_t addr;
+	uint8_t port_id;
+	uint16_t vf_id;
+	struct ether_addr mac_addr;
+
+};
+
+/* Common CLI fields for vf split drop enable disable */
+cmdline_parse_token_string_t cmd_set_vf_mac_addr_set =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_set_vf_mac_addr_result,
+		 set, "set");
+cmdline_parse_token_string_t cmd_set_vf_mac_addr_vf =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_set_vf_mac_addr_result,
+		 vf, "vf");
+cmdline_parse_token_string_t cmd_set_vf_mac_addr_mac =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_set_vf_mac_addr_result,
+		 mac, "mac");
+cmdline_parse_token_string_t cmd_set_vf_mac_addr_addr =
+	TOKEN_STRING_INITIALIZER
+		(struct cmd_set_vf_mac_addr_result,
+		 addr, "addr");
+cmdline_parse_token_num_t cmd_set_vf_mac_addr_port_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_set_vf_mac_addr_result,
+		 port_id, UINT8);
+cmdline_parse_token_num_t cmd_set_vf_mac_addr_vf_id =
+	TOKEN_NUM_INITIALIZER
+		(struct cmd_set_vf_mac_addr_result,
+		 vf_id, UINT16);
+cmdline_parse_token_etheraddr_t cmd_set_vf_mac_addr_mac_addr =
+	TOKEN_ETHERADDR_INITIALIZER(struct cmd_set_vf_mac_addr_result,
+		 mac_addr);
+
+static void
+cmd_set_vf_mac_addr_parsed(
+	void *parsed_result,
+	__attribute__((unused)) struct cmdline *cl,
+	__attribute__((unused)) void *data)
+{
+	struct cmd_set_vf_mac_addr_result *res = parsed_result;
+	int ret;
+
+	ret = rte_pmd_ixgbe_set_vf_mac_addr(res->port_id, res->vf_id,
+			&res->mac_addr);
+	switch (ret) {
+	case 0:
+		break;
+	case -EINVAL:
+		printf("invalid vf_id %d or mac_addr\n", res->vf_id);
+		break;
+	case -ENODEV:
+		printf("invalid port_id %d\n", res->port_id);
+		break;
+	default:
+		printf("programming error: (%s)\n", strerror(-ret));
+	}
+}
+
+cmdline_parse_inst_t cmd_set_vf_mac_addr = {
+	.f = cmd_set_vf_mac_addr_parsed,
+	.data = NULL,
+	.help_str = "set vf mac addr port_id vf_id xx:xx:xx:xx:xx:xx",
+	.tokens = {
+		(void *)&cmd_set_vf_mac_addr_set,
+		(void *)&cmd_set_vf_mac_addr_vf,
+		(void *)&cmd_set_vf_mac_addr_mac,
+		(void *)&cmd_set_vf_mac_addr_addr,
+		(void *)&cmd_set_vf_mac_addr_port_id,
+		(void *)&cmd_set_vf_mac_addr_vf_id,
+		(void *)&cmd_set_vf_mac_addr_mac_addr,
+		NULL,
+	},
+};
+#endif
 
 /* ******************************************************************************** */
 
@@ -10660,6 +11472,8 @@ cmdline_parse_ctx_t main_ctx[] = {
 	(cmdline_parse_inst_t *)&cmd_csum_tunnel,
 	(cmdline_parse_inst_t *)&cmd_tso_set,
 	(cmdline_parse_inst_t *)&cmd_tso_show,
+	(cmdline_parse_inst_t *)&cmd_tunnel_tso_set,
+	(cmdline_parse_inst_t *)&cmd_tunnel_tso_show,
 	(cmdline_parse_inst_t *)&cmd_link_flow_control_set,
 	(cmdline_parse_inst_t *)&cmd_link_flow_control_set_rx,
 	(cmdline_parse_inst_t *)&cmd_link_flow_control_set_tx,
@@ -10753,6 +11567,16 @@ cmdline_parse_ctx_t main_ctx[] = {
 	(cmdline_parse_inst_t *)&cmd_config_e_tag_forwarding_en_dis,
 	(cmdline_parse_inst_t *)&cmd_config_e_tag_filter_add,
 	(cmdline_parse_inst_t *)&cmd_config_e_tag_filter_del,
+#ifdef RTE_LIBRTE_IXGBE_PMD
+	(cmdline_parse_inst_t *)&cmd_set_vf_vlan_anti_spoof,
+	(cmdline_parse_inst_t *)&cmd_set_vf_mac_anti_spoof,
+	(cmdline_parse_inst_t *)&cmd_set_vf_vlan_stripq,
+	(cmdline_parse_inst_t *)&cmd_set_vf_vlan_insert,
+	(cmdline_parse_inst_t *)&cmd_set_tx_loopback,
+	(cmdline_parse_inst_t *)&cmd_set_all_queues_drop_en,
+	(cmdline_parse_inst_t *)&cmd_set_vf_split_drop_en,
+	(cmdline_parse_inst_t *)&cmd_set_vf_mac_addr,
+#endif
 	NULL,
 };
 
diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c
index 1457e4ad..36c47ab5 100644
--- a/app/test-pmd/config.c
+++ b/app/test-pmd/config.c
@@ -84,7 +84,6 @@
 #include <rte_lcore.h>
 #include <rte_atomic.h>
 #include <rte_branch_prediction.h>
-#include <rte_ring.h>
 #include <rte_mempool.h>
 #include <rte_mbuf.h>
 #include <rte_interrupts.h>
@@ -954,7 +953,7 @@ rxtx_config_display(void)
 	       rx_mode.hw_strip_crc ? "enabled" : "disabled",
 	       nb_pkt_per_burst);
 
-	if (cur_fwd_eng == &tx_only_engine)
+	if (cur_fwd_eng == &tx_only_engine || cur_fwd_eng == &flow_gen_engine)
 		printf("  packet len=%u - nb packet segments=%d\n",
 				(unsigned)tx_pkt_length, (int) tx_pkt_nb_segs);
 
diff --git a/app/test-pmd/csumonly.c b/app/test-pmd/csumonly.c
index ac4bd8f4..57e6ae27 100644
--- a/app/test-pmd/csumonly.c
+++ b/app/test-pmd/csumonly.c
@@ -56,7 +56,6 @@
 #include <rte_lcore.h>
 #include <rte_atomic.h>
 #include <rte_branch_prediction.h>
-#include <rte_ring.h>
 #include <rte_memory.h>
 #include <rte_mempool.h>
 #include <rte_mbuf.h>
@@ -102,6 +101,8 @@ struct testpmd_offload_info {
 	uint16_t outer_l3_len;
 	uint8_t outer_l4_proto;
 	uint16_t tso_segsz;
+	uint16_t tunnel_tso_segsz;
+	uint32_t pkt_len;
 };
 
 /* simplified GRE header */
@@ -318,21 +319,6 @@ parse_encap_ip(void *encap_ip, struct testpmd_offload_info *info)
 	info->l2_len = 0;
 }
 
-/* modify the IPv4 or IPv4 source address of a packet */
-static void
-change_ip_addresses(void *l3_hdr, uint16_t ethertype)
-{
-	struct ipv4_hdr *ipv4_hdr = l3_hdr;
-	struct ipv6_hdr *ipv6_hdr = l3_hdr;
-
-	if (ethertype == _htons(ETHER_TYPE_IPv4)) {
-		ipv4_hdr->src_addr =
-			rte_cpu_to_be_32(rte_be_to_cpu_32(ipv4_hdr->src_addr) + 1);
-	} else if (ethertype == _htons(ETHER_TYPE_IPv6)) {
-		ipv6_hdr->src_addr[15] = ipv6_hdr->src_addr[15] + 1;
-	}
-}
-
 /* if possible, calculate the checksum of a packet in hw or sw,
  * depending on the testpmd command line configuration */
 static uint64_t
@@ -344,13 +330,28 @@ process_inner_cksums(void *l3_hdr, const struct testpmd_offload_info *info,
 	struct tcp_hdr *tcp_hdr;
 	struct sctp_hdr *sctp_hdr;
 	uint64_t ol_flags = 0;
+	uint32_t max_pkt_len, tso_segsz = 0;
+
+	/* ensure packet is large enough to require tso */
+	if (!info->is_tunnel) {
+		max_pkt_len = info->l2_len + info->l3_len + info->l4_len +
+			info->tso_segsz;
+		if (info->tso_segsz != 0 && info->pkt_len > max_pkt_len)
+			tso_segsz = info->tso_segsz;
+	} else {
+		max_pkt_len = info->outer_l2_len + info->outer_l3_len +
+			info->l2_len + info->l3_len + info->l4_len +
+			info->tunnel_tso_segsz;
+		if (info->tunnel_tso_segsz != 0 && info->pkt_len > max_pkt_len)
+			tso_segsz = info->tunnel_tso_segsz;
+	}
 
 	if (info->ethertype == _htons(ETHER_TYPE_IPv4)) {
 		ipv4_hdr = l3_hdr;
 		ipv4_hdr->hdr_checksum = 0;
 
 		ol_flags |= PKT_TX_IPV4;
-		if (info->tso_segsz != 0 && info->l4_proto == IPPROTO_TCP) {
+		if (info->l4_proto == IPPROTO_TCP && tso_segsz) {
 			ol_flags |= PKT_TX_IP_CKSUM;
 		} else {
 			if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_IP_CKSUM)
@@ -382,7 +383,7 @@ process_inner_cksums(void *l3_hdr, const struct testpmd_offload_info *info,
 	} else if (info->l4_proto == IPPROTO_TCP) {
 		tcp_hdr = (struct tcp_hdr *)((char *)l3_hdr + info->l3_len);
 		tcp_hdr->cksum = 0;
-		if (info->tso_segsz != 0) {
+		if (tso_segsz) {
 			ol_flags |= PKT_TX_TCP_SEG;
 			tcp_hdr->cksum = get_psd_sum(l3_hdr, info->ethertype,
 				ol_flags);
@@ -412,12 +413,10 @@ process_inner_cksums(void *l3_hdr, const struct testpmd_offload_info *info,
 	return ol_flags;
 }
 
-/* Calculate the checksum of outer header (only vxlan is supported,
- * meaning IP + UDP). The caller already checked that it's a vxlan
- * packet */
+/* Calculate the checksum of outer header */
 static uint64_t
 process_outer_cksums(void *outer_l3_hdr, struct testpmd_offload_info *info,
-	uint16_t testpmd_ol_flags)
+	uint16_t testpmd_ol_flags, int tso_enabled)
 {
 	struct ipv4_hdr *ipv4_hdr = outer_l3_hdr;
 	struct ipv6_hdr *ipv6_hdr = outer_l3_hdr;
@@ -438,10 +437,20 @@ process_outer_cksums(void *outer_l3_hdr, struct testpmd_offload_info *info,
 	if (info->outer_l4_proto != IPPROTO_UDP)
 		return ol_flags;
 
-	/* outer UDP checksum is always done in software as we have no
-	 * hardware supporting it today, and no API for it. */
-
 	udp_hdr = (struct udp_hdr *)((char *)outer_l3_hdr + info->outer_l3_len);
+
+	/* outer UDP checksum is done in software as we have no hardware
+	 * supporting it today, and no API for it. In the other side, for
+	 * UDP tunneling, like VXLAN or Geneve, outer UDP checksum can be
+	 * set to zero.
+	 *
+	 * If a packet will be TSOed into small packets by NIC, we cannot
+	 * set/calculate a non-zero checksum, because it will be a wrong
+	 * value after the packet be split into several small packets.
+	 */
+	if (tso_enabled)
+		udp_hdr->dgram_cksum = 0;
+
 	/* do not recalculate udp cksum if it was 0 */
 	if (udp_hdr->dgram_cksum != 0) {
 		udp_hdr->dgram_cksum = 0;
@@ -609,7 +618,6 @@ pkt_copy_split(const struct rte_mbuf *pkt)
  * Receive a burst of packets, and for each packet:
  *  - parse packet, and try to recognize a supported packet type (1)
  *  - if it's not a supported packet type, don't touch the packet, else:
- *  - modify the IPs in inner headers and in outer headers if any
  *  - reprocess the checksum of all supported layers. This is done in SW
  *    or HW, depending on testpmd command line configuration
  *  - if TSO is enabled in testpmd command line, also flag the mbuf for TCP
@@ -641,7 +649,7 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
 	uint16_t nb_rx;
 	uint16_t nb_tx;
 	uint16_t i;
-	uint64_t ol_flags;
+	uint64_t rx_ol_flags, tx_ol_flags;
 	uint16_t testpmd_ol_flags;
 	uint32_t retry;
 	uint32_t rx_bad_ip_csum;
@@ -675,19 +683,24 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
 	testpmd_ol_flags = txp->tx_ol_flags;
 	memset(&info, 0, sizeof(info));
 	info.tso_segsz = txp->tso_segsz;
+	info.tunnel_tso_segsz = txp->tunnel_tso_segsz;
 
 	for (i = 0; i < nb_rx; i++) {
 		if (likely(i < nb_rx - 1))
 			rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i + 1],
 						       void *));
 
-		ol_flags = 0;
-		info.is_tunnel = 0;
 		m = pkts_burst[i];
+		info.is_tunnel = 0;
+		info.pkt_len = rte_pktmbuf_pkt_len(m);
+		tx_ol_flags = 0;
+		rx_ol_flags = m->ol_flags;
 
 		/* Update the L3/L4 checksum error packet statistics */
-		rx_bad_ip_csum += ((m->ol_flags & PKT_RX_IP_CKSUM_BAD) != 0);
-		rx_bad_l4_csum += ((m->ol_flags & PKT_RX_L4_CKSUM_BAD) != 0);
+		if ((rx_ol_flags & PKT_RX_IP_CKSUM_MASK) == PKT_RX_IP_CKSUM_BAD)
+			rx_bad_ip_csum += 1;
+		if ((rx_ol_flags & PKT_RX_L4_CKSUM_MASK) == PKT_RX_L4_CKSUM_BAD)
+			rx_bad_l4_csum += 1;
 
 		/* step 1: dissect packet, parsing optional vlan, ip4/ip6, vxlan
 		 * and inner headers */
@@ -704,18 +717,27 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
 		if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_PARSE_TUNNEL) {
 			if (info.l4_proto == IPPROTO_UDP) {
 				struct udp_hdr *udp_hdr;
+
 				udp_hdr = (struct udp_hdr *)((char *)l3_hdr +
 					info.l3_len);
 				parse_vxlan(udp_hdr, &info, m->packet_type);
+				if (info.is_tunnel)
+					tx_ol_flags |= PKT_TX_TUNNEL_VXLAN;
 			} else if (info.l4_proto == IPPROTO_GRE) {
 				struct simple_gre_hdr *gre_hdr;
+
 				gre_hdr = (struct simple_gre_hdr *)
 					((char *)l3_hdr + info.l3_len);
 				parse_gre(gre_hdr, &info);
+				if (info.is_tunnel)
+					tx_ol_flags |= PKT_TX_TUNNEL_GRE;
 			} else if (info.l4_proto == IPPROTO_IPIP) {
 				void *encap_ip_hdr;
+
 				encap_ip_hdr = (char *)l3_hdr + info.l3_len;
 				parse_encap_ip(encap_ip_hdr, &info);
+				if (info.is_tunnel)
+					tx_ol_flags |= PKT_TX_TUNNEL_IPIP;
 			}
 		}
 
@@ -725,38 +747,35 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
 			l3_hdr = (char *)l3_hdr + info.outer_l3_len + info.l2_len;
 		}
 
-		/* step 2: change all source IPs (v4 or v6) so we need
-		 * to recompute the chksums even if they were correct */
-
-		change_ip_addresses(l3_hdr, info.ethertype);
-		if (info.is_tunnel == 1)
-			change_ip_addresses(outer_l3_hdr, info.outer_ethertype);
-
-		/* step 3: depending on user command line configuration,
+		/* step 2: depending on user command line configuration,
 		 * recompute checksum either in software or flag the
 		 * mbuf to offload the calculation to the NIC. If TSO
 		 * is configured, prepare the mbuf for TCP segmentation. */
 
 		/* process checksums of inner headers first */
-		ol_flags |= process_inner_cksums(l3_hdr, &info, testpmd_ol_flags);
+		tx_ol_flags |= process_inner_cksums(l3_hdr, &info,
+			testpmd_ol_flags);
 
 		/* Then process outer headers if any. Note that the software
 		 * checksum will be wrong if one of the inner checksums is
 		 * processed in hardware. */
 		if (info.is_tunnel == 1) {
-			ol_flags |= process_outer_cksums(outer_l3_hdr, &info,
-				testpmd_ol_flags);
+			tx_ol_flags |= process_outer_cksums(outer_l3_hdr, &info,
+					testpmd_ol_flags,
+					!!(tx_ol_flags & PKT_TX_TCP_SEG));
 		}
 
-		/* step 4: fill the mbuf meta data (flags and header lengths) */
+		/* step 3: fill the mbuf meta data (flags and header lengths) */
 
 		if (info.is_tunnel == 1) {
-			if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM) {
+			if (info.tunnel_tso_segsz ||
+			    testpmd_ol_flags & TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM) {
 				m->outer_l2_len = info.outer_l2_len;
 				m->outer_l3_len = info.outer_l3_len;
 				m->l2_len = info.l2_len;
 				m->l3_len = info.l3_len;
 				m->l4_len = info.l4_len;
+				m->tso_segsz = info.tunnel_tso_segsz;
 			}
 			else {
 				/* if there is a outer UDP cksum
@@ -776,9 +795,9 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
 			m->l2_len = info.l2_len;
 			m->l3_len = info.l3_len;
 			m->l4_len = info.l4_len;
+			m->tso_segsz = info.tso_segsz;
 		}
-		m->tso_segsz = info.tso_segsz;
-		m->ol_flags = ol_flags;
+		m->ol_flags = tx_ol_flags;
 
 		/* Do split & copy for the packet. */
 		if (tx_pkt_split != TX_PKT_SPLIT_OFF) {
@@ -792,32 +811,19 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
 
 		/* if verbose mode is enabled, dump debug info */
 		if (verbose_level > 0) {
-			struct {
-				uint64_t flag;
-				uint64_t mask;
-			} tx_flags[] = {
-				{ PKT_TX_IP_CKSUM, PKT_TX_IP_CKSUM },
-				{ PKT_TX_UDP_CKSUM, PKT_TX_L4_MASK },
-				{ PKT_TX_TCP_CKSUM, PKT_TX_L4_MASK },
-				{ PKT_TX_SCTP_CKSUM, PKT_TX_L4_MASK },
-				{ PKT_TX_IPV4, PKT_TX_IPV4 },
-				{ PKT_TX_IPV6, PKT_TX_IPV6 },
-				{ PKT_TX_OUTER_IP_CKSUM, PKT_TX_OUTER_IP_CKSUM },
-				{ PKT_TX_OUTER_IPV4, PKT_TX_OUTER_IPV4 },
-				{ PKT_TX_OUTER_IPV6, PKT_TX_OUTER_IPV6 },
-				{ PKT_TX_TCP_SEG, PKT_TX_TCP_SEG },
-			};
-			unsigned j;
-			const char *name;
+			char buf[256];
 
 			printf("-----------------\n");
-			printf("mbuf=%p, pkt_len=%u, nb_segs=%hhu:\n",
-				m, m->pkt_len, m->nb_segs);
+			printf("port=%u, mbuf=%p, pkt_len=%u, nb_segs=%hhu:\n",
+				fs->rx_port, m, m->pkt_len, m->nb_segs);
 			/* dump rx parsed packet info */
+			rte_get_rx_ol_flag_list(rx_ol_flags, buf, sizeof(buf));
 			printf("rx: l2_len=%d ethertype=%x l3_len=%d "
-				"l4_proto=%d l4_len=%d\n",
+				"l4_proto=%d l4_len=%d flags=%s\n",
 				info.l2_len, rte_be_to_cpu_16(info.ethertype),
-				info.l3_len, info.l4_proto, info.l4_len);
+				info.l3_len, info.l4_proto, info.l4_len, buf);
+			if (rx_ol_flags & PKT_RX_LRO)
+				printf("rx: m->lro_segsz=%u\n", m->tso_segsz);
 			if (info.is_tunnel == 1)
 				printf("rx: outer_l2_len=%d outer_ethertype=%x "
 					"outer_l3_len=%d\n", info.outer_l2_len,
@@ -832,19 +838,22 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
 				printf("tx: m->l2_len=%d m->l3_len=%d "
 					"m->l4_len=%d\n",
 					m->l2_len, m->l3_len, m->l4_len);
-			if ((info.is_tunnel == 1) &&
-				(testpmd_ol_flags & TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM))
-				printf("tx: m->outer_l2_len=%d m->outer_l3_len=%d\n",
-					m->outer_l2_len, m->outer_l3_len);
-			if (info.tso_segsz != 0)
+			if (info.is_tunnel == 1) {
+				if (testpmd_ol_flags &
+				    TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM)
+					printf("tx: m->outer_l2_len=%d "
+						"m->outer_l3_len=%d\n",
+						m->outer_l2_len,
+						m->outer_l3_len);
+				if (info.tunnel_tso_segsz != 0 &&
+						(m->ol_flags & PKT_TX_TCP_SEG))
+					printf("tx: m->tso_segsz=%d\n",
+						m->tso_segsz);
+			} else if (info.tso_segsz != 0 &&
+					(m->ol_flags & PKT_TX_TCP_SEG))
 				printf("tx: m->tso_segsz=%d\n", m->tso_segsz);
-			printf("tx: flags=");
-			for (j = 0; j < sizeof(tx_flags)/sizeof(*tx_flags); j++) {
-				name = rte_get_tx_ol_flag_name(tx_flags[j].flag);
-				if ((m->ol_flags & tx_flags[j].mask) ==
-					tx_flags[j].flag)
-					printf("%s ", name);
-			}
+			rte_get_tx_ol_flag_list(m->ol_flags, buf, sizeof(buf));
+			printf("tx: flags=%s", buf);
 			printf("\n");
 		}
 	}
diff --git a/app/test-pmd/flowgen.c b/app/test-pmd/flowgen.c
index a6abe91e..b13ff89a 100644
--- a/app/test-pmd/flowgen.c
+++ b/app/test-pmd/flowgen.c
@@ -57,7 +57,6 @@
 #include <rte_lcore.h>
 #include <rte_atomic.h>
 #include <rte_branch_prediction.h>
-#include <rte_ring.h>
 #include <rte_memory.h>
 #include <rte_mempool.h>
 #include <rte_mbuf.h>
@@ -74,7 +73,6 @@
 
 /* hardcoded configuration (for now) */
 static unsigned cfg_n_flows	= 1024;
-static unsigned cfg_pkt_size	= 300;
 static uint32_t cfg_ip_src	= IPv4(10, 254, 0, 0);
 static uint32_t cfg_ip_dst	= IPv4(10, 253, 0, 0);
 static uint16_t cfg_udp_src	= 1000;
@@ -118,7 +116,7 @@ ip_sum(const unaligned_uint16_t *hdr, int hdr_len)
 static void
 pkt_burst_flow_gen(struct fwd_stream *fs)
 {
-	unsigned pkt_size = cfg_pkt_size - 4;	/* Adjust FCS */
+	unsigned pkt_size = tx_pkt_length - 4;	/* Adjust FCS */
 	struct rte_mbuf  *pkts_burst[MAX_PKT_BURST];
 	struct rte_mempool *mbp;
 	struct rte_mbuf  *pkt;
diff --git a/app/test-pmd/icmpecho.c b/app/test-pmd/icmpecho.c
index be308c9f..6a4e750f 100644
--- a/app/test-pmd/icmpecho.c
+++ b/app/test-pmd/icmpecho.c
@@ -52,7 +52,6 @@
 #include <rte_lcore.h>
 #include <rte_atomic.h>
 #include <rte_branch_prediction.h>
-#include <rte_ring.h>
 #include <rte_memory.h>
 #include <rte_mempool.h>
 #include <rte_mbuf.h>
diff --git a/app/test-pmd/iofwd.c b/app/test-pmd/iofwd.c
index 7b6033a5..26936b7b 100644
--- a/app/test-pmd/iofwd.c
+++ b/app/test-pmd/iofwd.c
@@ -55,7 +55,6 @@
 #include <rte_lcore.h>
 #include <rte_atomic.h>
 #include <rte_branch_prediction.h>
-#include <rte_ring.h>
 #include <rte_memory.h>
 #include <rte_memcpy.h>
 #include <rte_mempool.h>
diff --git a/app/test-pmd/macfwd.c b/app/test-pmd/macfwd.c
index 5d1c1617..86e01dea 100644
--- a/app/test-pmd/macfwd.c
+++ b/app/test-pmd/macfwd.c
@@ -56,7 +56,6 @@
 #include <rte_lcore.h>
 #include <rte_atomic.h>
 #include <rte_branch_prediction.h>
-#include <rte_ring.h>
 #include <rte_memory.h>
 #include <rte_mempool.h>
 #include <rte_mbuf.h>
diff --git a/app/test-pmd/macswap.c b/app/test-pmd/macswap.c
index 4b0dbeb5..36e139f6 100644
--- a/app/test-pmd/macswap.c
+++ b/app/test-pmd/macswap.c
@@ -56,7 +56,6 @@
 #include <rte_lcore.h>
 #include <rte_atomic.h>
 #include <rte_branch_prediction.h>
-#include <rte_ring.h>
 #include <rte_memory.h>
 #include <rte_mempool.h>
 #include <rte_mbuf.h>
diff --git a/app/test-pmd/parameters.c b/app/test-pmd/parameters.c
index 8792c2c6..08e5a76f 100644
--- a/app/test-pmd/parameters.c
+++ b/app/test-pmd/parameters.c
@@ -63,7 +63,6 @@
 #include <rte_lcore.h>
 #include <rte_atomic.h>
 #include <rte_branch_prediction.h>
-#include <rte_ring.h>
 #include <rte_mempool.h>
 #include <rte_interrupts.h>
 #include <rte_pci.h>
@@ -150,6 +149,7 @@ usage(char* progname)
 	       "If the drop-queue doesn't exist, the packet is dropped. "
 	       "By default drop-queue=127.\n");
 	printf("  --crc-strip: enable CRC stripping by hardware.\n");
+	printf("  --enable-lro: enable large receive offload.\n");
 	printf("  --enable-rx-cksum: enable rx hardware checksum offload.\n");
 	printf("  --disable-hw-vlan: disable hardware vlan.\n");
 	printf("  --disable-hw-vlan-filter: disable hardware vlan filter.\n");
@@ -191,7 +191,8 @@ usage(char* progname)
 	       "(0 <= mapping <= %d).\n", RTE_ETHDEV_QUEUE_STAT_CNTRS - 1);
 	printf("  --no-flush-rx: Don't flush RX streams before forwarding."
 	       " Used mainly with PCAP drivers.\n");
-	printf("  --txpkts=X[,Y]*: set TX segment sizes.\n");
+	printf("  --txpkts=X[,Y]*: set TX segment sizes"
+		" or total packet length.\n");
 	printf("  --disable-link-check: disable check on link status when "
 	       "starting/stopping ports.\n");
 }
@@ -525,6 +526,7 @@ launch_args_parse(int argc, char** argv)
 		{ "pkt-filter-size",            1, 0, 0 },
 		{ "pkt-filter-drop-queue",      1, 0, 0 },
 		{ "crc-strip",                  0, 0, 0 },
+		{ "enable-lro",                 0, 0, 0 },
 		{ "enable-rx-cksum",            0, 0, 0 },
 		{ "enable-scatter",             0, 0, 0 },
 		{ "disable-hw-vlan",            0, 0, 0 },
@@ -765,6 +767,8 @@ launch_args_parse(int argc, char** argv)
 			}
 			if (!strcmp(lgopts[opt_idx].name, "crc-strip"))
 				rx_mode.hw_strip_crc = 1;
+			if (!strcmp(lgopts[opt_idx].name, "enable-lro"))
+				rx_mode.enable_lro = 1;
 			if (!strcmp(lgopts[opt_idx].name, "enable-scatter"))
 				rx_mode.enable_scatter = 1;
 			if (!strcmp(lgopts[opt_idx].name, "enable-rx-cksum"))
diff --git a/app/test-pmd/rxonly.c b/app/test-pmd/rxonly.c
index fbf287dc..fff815c6 100644
--- a/app/test-pmd/rxonly.c
+++ b/app/test-pmd/rxonly.c
@@ -56,7 +56,6 @@
 #include <rte_lcore.h>
 #include <rte_atomic.h>
 #include <rte_branch_prediction.h>
-#include <rte_ring.h>
 #include <rte_memory.h>
 #include <rte_mempool.h>
 #include <rte_mbuf.h>
@@ -67,6 +66,7 @@
 #include <rte_string_fns.h>
 #include <rte_ip.h>
 #include <rte_udp.h>
+#include <rte_net.h>
 
 #include "testpmd.h"
 
@@ -92,6 +92,9 @@ pkt_burst_receive(struct fwd_stream *fs)
 	uint16_t nb_rx;
 	uint16_t i, packet_type;
 	uint16_t is_encapsulation;
+	char buf[256];
+	struct rte_net_hdr_lens hdr_lens;
+	uint32_t sw_packet_type;
 
 #ifdef RTE_TEST_PMD_RECORD_CORE_CYCLES
 	uint64_t start_tsc;
@@ -162,177 +165,27 @@ pkt_burst_receive(struct fwd_stream *fs)
 			printf(" - QinQ VLAN tci=0x%x, VLAN tci outer=0x%x",
 					mb->vlan_tci, mb->vlan_tci_outer);
 		if (mb->packet_type) {
-			uint32_t ptype;
-
-			/* (outer) L2 packet type */
-			ptype = mb->packet_type & RTE_PTYPE_L2_MASK;
-			switch (ptype) {
-			case RTE_PTYPE_L2_ETHER:
-				printf(" - (outer) L2 type: ETHER");
-				break;
-			case RTE_PTYPE_L2_ETHER_TIMESYNC:
-				printf(" - (outer) L2 type: ETHER_Timesync");
-				break;
-			case RTE_PTYPE_L2_ETHER_ARP:
-				printf(" - (outer) L2 type: ETHER_ARP");
-				break;
-			case RTE_PTYPE_L2_ETHER_LLDP:
-				printf(" - (outer) L2 type: ETHER_LLDP");
-				break;
-			case RTE_PTYPE_L2_ETHER_NSH:
-				printf(" - (outer) L2 type: ETHER_NSH");
-				break;
-			default:
-				printf(" - (outer) L2 type: Unknown");
-				break;
-			}
-
-			/* (outer) L3 packet type */
-			ptype = mb->packet_type & RTE_PTYPE_L3_MASK;
-			switch (ptype) {
-			case RTE_PTYPE_L3_IPV4:
-				printf(" - (outer) L3 type: IPV4");
-				break;
-			case RTE_PTYPE_L3_IPV4_EXT:
-				printf(" - (outer) L3 type: IPV4_EXT");
-				break;
-			case RTE_PTYPE_L3_IPV6:
-				printf(" - (outer) L3 type: IPV6");
-				break;
-			case RTE_PTYPE_L3_IPV4_EXT_UNKNOWN:
-				printf(" - (outer) L3 type: IPV4_EXT_UNKNOWN");
-				break;
-			case RTE_PTYPE_L3_IPV6_EXT:
-				printf(" - (outer) L3 type: IPV6_EXT");
-				break;
-			case RTE_PTYPE_L3_IPV6_EXT_UNKNOWN:
-				printf(" - (outer) L3 type: IPV6_EXT_UNKNOWN");
-				break;
-			default:
-				printf(" - (outer) L3 type: Unknown");
-				break;
-			}
-
-			/* (outer) L4 packet type */
-			ptype = mb->packet_type & RTE_PTYPE_L4_MASK;
-			switch (ptype) {
-			case RTE_PTYPE_L4_TCP:
-				printf(" - (outer) L4 type: TCP");
-				break;
-			case RTE_PTYPE_L4_UDP:
-				printf(" - (outer) L4 type: UDP");
-				break;
-			case RTE_PTYPE_L4_FRAG:
-				printf(" - (outer) L4 type: L4_FRAG");
-				break;
-			case RTE_PTYPE_L4_SCTP:
-				printf(" - (outer) L4 type: SCTP");
-				break;
-			case RTE_PTYPE_L4_ICMP:
-				printf(" - (outer) L4 type: ICMP");
-				break;
-			case RTE_PTYPE_L4_NONFRAG:
-				printf(" - (outer) L4 type: L4_NONFRAG");
-				break;
-			default:
-				printf(" - (outer) L4 type: Unknown");
-				break;
-			}
-
-			/* packet tunnel type */
-			ptype = mb->packet_type & RTE_PTYPE_TUNNEL_MASK;
-			switch (ptype) {
-			case RTE_PTYPE_TUNNEL_IP:
-				printf(" - Tunnel type: IP");
-				break;
-			case RTE_PTYPE_TUNNEL_GRE:
-				printf(" - Tunnel type: GRE");
-				break;
-			case RTE_PTYPE_TUNNEL_VXLAN:
-				printf(" - Tunnel type: VXLAN");
-				break;
-			case RTE_PTYPE_TUNNEL_NVGRE:
-				printf(" - Tunnel type: NVGRE");
-				break;
-			case RTE_PTYPE_TUNNEL_GENEVE:
-				printf(" - Tunnel type: GENEVE");
-				break;
-			case RTE_PTYPE_TUNNEL_GRENAT:
-				printf(" - Tunnel type: GRENAT");
-				break;
-			default:
-				printf(" - Tunnel type: Unknown");
-				break;
-			}
-
-			/* inner L2 packet type */
-			ptype = mb->packet_type & RTE_PTYPE_INNER_L2_MASK;
-			switch (ptype) {
-			case RTE_PTYPE_INNER_L2_ETHER:
-				printf(" - Inner L2 type: ETHER");
-				break;
-			case RTE_PTYPE_INNER_L2_ETHER_VLAN:
-				printf(" - Inner L2 type: ETHER_VLAN");
-				break;
-			default:
-				printf(" - Inner L2 type: Unknown");
-				break;
-			}
-
-			/* inner L3 packet type */
-			ptype = mb->packet_type & RTE_PTYPE_INNER_L3_MASK;
-			switch (ptype) {
-			case RTE_PTYPE_INNER_L3_IPV4:
-				printf(" - Inner L3 type: IPV4");
-				break;
-			case RTE_PTYPE_INNER_L3_IPV4_EXT:
-				printf(" - Inner L3 type: IPV4_EXT");
-				break;
-			case RTE_PTYPE_INNER_L3_IPV6:
-				printf(" - Inner L3 type: IPV6");
-				break;
-			case RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN:
-				printf(" - Inner L3 type: IPV4_EXT_UNKNOWN");
-				break;
-			case RTE_PTYPE_INNER_L3_IPV6_EXT:
-				printf(" - Inner L3 type: IPV6_EXT");
-				break;
-			case RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN:
-				printf(" - Inner L3 type: IPV6_EXT_UNKNOWN");
-				break;
-			default:
-				printf(" - Inner L3 type: Unknown");
-				break;
-			}
-
-			/* inner L4 packet type */
-			ptype = mb->packet_type & RTE_PTYPE_INNER_L4_MASK;
-			switch (ptype) {
-			case RTE_PTYPE_INNER_L4_TCP:
-				printf(" - Inner L4 type: TCP");
-				break;
-			case RTE_PTYPE_INNER_L4_UDP:
-				printf(" - Inner L4 type: UDP");
-				break;
-			case RTE_PTYPE_INNER_L4_FRAG:
-				printf(" - Inner L4 type: L4_FRAG");
-				break;
-			case RTE_PTYPE_INNER_L4_SCTP:
-				printf(" - Inner L4 type: SCTP");
-				break;
-			case RTE_PTYPE_INNER_L4_ICMP:
-				printf(" - Inner L4 type: ICMP");
-				break;
-			case RTE_PTYPE_INNER_L4_NONFRAG:
-				printf(" - Inner L4 type: L4_NONFRAG");
-				break;
-			default:
-				printf(" - Inner L4 type: Unknown");
-				break;
-			}
-			printf("\n");
-		} else
-			printf("Unknown packet type\n");
+			rte_get_ptype_name(mb->packet_type, buf, sizeof(buf));
+			printf(" - hw ptype: %s", buf);
+		}
+		sw_packet_type = rte_net_get_ptype(mb, &hdr_lens,
+			RTE_PTYPE_ALL_MASK);
+		rte_get_ptype_name(sw_packet_type, buf, sizeof(buf));
+		printf(" - sw ptype: %s", buf);
+		if (sw_packet_type & RTE_PTYPE_L2_MASK)
+			printf(" - l2_len=%d", hdr_lens.l2_len);
+		if (sw_packet_type & RTE_PTYPE_L3_MASK)
+			printf(" - l3_len=%d", hdr_lens.l3_len);
+		if (sw_packet_type & RTE_PTYPE_L4_MASK)
+			printf(" - l4_len=%d", hdr_lens.l4_len);
+		if (sw_packet_type & RTE_PTYPE_TUNNEL_MASK)
+			printf(" - tunnel_len=%d", hdr_lens.tunnel_len);
+		if (sw_packet_type & RTE_PTYPE_INNER_L2_MASK)
+			printf(" - inner_l2_len=%d", hdr_lens.inner_l2_len);
+		if (sw_packet_type & RTE_PTYPE_INNER_L3_MASK)
+			printf(" - inner_l3_len=%d", hdr_lens.inner_l3_len);
+		if (sw_packet_type & RTE_PTYPE_INNER_L4_MASK)
+			printf(" - inner_l4_len=%d", hdr_lens.inner_l4_len);
 		if (is_encapsulation) {
 			struct ipv4_hdr *ipv4_hdr;
 			struct ipv6_hdr *ipv6_hdr;
@@ -376,19 +229,8 @@ pkt_burst_receive(struct fwd_stream *fs)
 		}
 		printf(" - Receive queue=0x%x", (unsigned) fs->rx_queue);
 		printf("\n");
-		if (ol_flags != 0) {
-			unsigned rxf;
-			const char *name;
-
-			for (rxf = 0; rxf < sizeof(mb->ol_flags) * 8; rxf++) {
-				if ((ol_flags & (1ULL << rxf)) == 0)
-					continue;
-				name = rte_get_rx_ol_flag_name(1ULL << rxf);
-				if (name == NULL)
-					continue;
-				printf("  %s\n", name);
-			}
-		}
+		rte_get_rx_ol_flag_list(mb->ol_flags, buf, sizeof(buf));
+		printf("  ol_flags: %s\n", buf);
 		rte_pktmbuf_free(mb);
 	}
 
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index 8d0905eb..a0332c26 100644
--- a/app/test-pmd/testpmd.c
+++ b/app/test-pmd/testpmd.c
@@ -63,7 +63,6 @@
 #include <rte_lcore.h>
 #include <rte_atomic.h>
 #include <rte_branch_prediction.h>
-#include <rte_ring.h>
 #include <rte_mempool.h>
 #include <rte_malloc.h>
 #include <rte_mbuf.h>
diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h
index 74bf5cb4..9c1e7039 100644
--- a/app/test-pmd/testpmd.h
+++ b/app/test-pmd/testpmd.h
@@ -158,7 +158,8 @@ struct rte_port {
 	struct fwd_stream       *tx_stream; /**< Port TX stream, if unique */
 	unsigned int            socket_id;  /**< For NUMA support */
 	uint16_t                tx_ol_flags;/**< TX Offload Flags (TESTPMD_TX_OFFLOAD...). */
-	uint16_t                tso_segsz;  /**< MSS for segmentation offload. */
+	uint16_t                tso_segsz;  /**< Segmentation offload MSS for non-tunneled packets. */
+	uint16_t                tunnel_tso_segsz; /**< Segmentation offload MSS for tunneled pkts. */
 	uint16_t                tx_vlan_id;/**< The tag ID */
 	uint16_t                tx_vlan_id_outer;/**< The outer tag ID */
 	void                    *fwd_ctx;   /**< Forwarding mode context */
diff --git a/app/test-pmd/txonly.c b/app/test-pmd/txonly.c
index 11fd681d..8513a062 100644
--- a/app/test-pmd/txonly.c
+++ b/app/test-pmd/txonly.c
@@ -56,7 +56,6 @@
 #include <rte_lcore.h>
 #include <rte_atomic.h>
 #include <rte_branch_prediction.h>
-#include <rte_ring.h>
 #include <rte_memory.h>
 #include <rte_mempool.h>
 #include <rte_mbuf.h>
@@ -223,6 +222,14 @@ pkt_burst_transmit(struct fwd_stream *fs)
 				return;
 			break;
 		}
+
+		/*
+		 * Using raw alloc is good to improve performance,
+		 * but some consumers may use the headroom and so
+		 * decrement data_off. We need to make sure it is
+		 * reset to default value.
+		 */
+		rte_pktmbuf_reset_headroom(pkt);
 		pkt->data_len = tx_pkt_seg_lengths[0];
 		pkt_seg = pkt;
 		if (tx_pkt_split == TX_PKT_SPLIT_RND)