Re: [dpdk-dev] [PATCH v2 08/13] testpmd: rework csum forward engine

["Liu, Jijiang" <jijiang.liu@intel.com>]

> -----Original Message-----
> From: Olivier Matz [mailto:olivier.matz@6wind.com]
> Sent: Saturday, November 15, 2014 1:03 AM
> To: dev@dpdk.org
> Cc: olivier.matz@6wind.com; Walukiewicz, Miroslaw; Liu, Jijiang; Liu, Yong;
> jigsaw@gmail.com; Richardson, Bruce
> Subject: [PATCH v2 08/13] testpmd: rework csum forward engine
> 
> The csum forward engine was becoming too complex to be used and extended
> (the next commits want to add the support of TSO):
> 
> - no explaination about what the code does
> - code is not factorized, lots of code duplicated, especially between
>   ipv4/ipv6
> - user command line api: use of bitmasks that need to be calculated by
>   the user
> - the user flags don't have the same semantic:
>   - for legacy IP/UDP/TCP/SCTP, it selects software or hardware checksum
>   - for other (vxlan), it selects between hardware checksum or no
>     checksum
> - the code relies too much on flags set by the driver without software
>   alternative (ex: PKT_RX_TUNNEL_IPV4_HDR). It is nice to be able to
>   compare a software implementation with the hardware offload.
> 
> This commit tries to fix these issues, and provide a simple definition of what is
> done by the forward engine:
> 
>  * Receive a burst of packets, and for supported packet types:
>  *  - modify the IPs
>  *  - reprocess the checksum in SW or HW, depending on testpmd command line
>  *    configuration
>  * Then packets are transmitted on the output port.
>  *
>  * Supported packets are:
>  *   Ether / (vlan) / IP|IP6 / UDP|TCP|SCTP .
>  *   Ether / (vlan) / IP|IP6 / UDP / VxLAN / Ether / IP|IP6 / UDP|TCP|SCTP
>  *
>  * The network parser supposes that the packet is contiguous, which may
>  * not be the case in real life.
> 
> Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
> ---
>  app/test-pmd/cmdline.c  | 151 ++++++++---
>  app/test-pmd/config.c   |  11 -
>  app/test-pmd/csumonly.c | 668 ++++++++++++++++++++++-------------------------
> -
>  app/test-pmd/testpmd.h  |  17 +-
>  4 files changed, 423 insertions(+), 424 deletions(-)
> 
> diff --git a/app/test-pmd/cmdline.c b/app/test-pmd/cmdline.c index
> 4c3fc76..0361e58 100644
> --- a/app/test-pmd/cmdline.c
> +++ b/app/test-pmd/cmdline.c
> @@ -310,19 +310,14 @@ static void cmd_help_long_parsed(void
> *parsed_result,
>  			"    Disable hardware insertion of a VLAN header in"
>  			" packets sent on a port.\n\n"
> 
> -			"tx_checksum set (mask) (port_id)\n"
> -			"    Enable hardware insertion of checksum offload with"
> -			" the 8-bit mask, 0~0xff, in packets sent on a port.\n"
> -			"        bit 0 - insert ip   checksum offload if set\n"
> -			"        bit 1 - insert udp  checksum offload if set\n"
> -			"        bit 2 - insert tcp  checksum offload if set\n"
> -			"        bit 3 - insert sctp checksum offload if set\n"
> -			"        bit 4 - insert inner ip  checksum offload if set\n"
> -			"        bit 5 - insert inner udp checksum offload if set\n"
> -			"        bit 6 - insert inner tcp checksum offload if set\n"
> -			"        bit 7 - insert inner sctp checksum offload if set\n"
> +			"tx_cksum set (ip|udp|tcp|sctp|vxlan) (hw|sw)
> (port_id)\n"
> +			"    Enable hardware calculation of checksum with when"
> +			" transmitting a packet using 'csum' forward engine.\n"
>  			"    Please check the NIC datasheet for HW limits.\n\n"
> 
> +			"tx_checksum show (port_id)\n"
> +			"    Display tx checksum offload configuration\n\n"
> +
>  			"set fwd (%s)\n"
>  			"    Set packet forwarding mode.\n\n"
> 
> @@ -2738,48 +2733,131 @@ cmdline_parse_inst_t cmd_tx_vlan_reset = {
> 
> 
>  /* *** ENABLE HARDWARE INSERTION OF CHECKSUM IN TX PACKETS *** */ -
> struct cmd_tx_cksum_set_result {
> +struct cmd_tx_cksum_result {
>  	cmdline_fixed_string_t tx_cksum;
> -	cmdline_fixed_string_t set;
> -	uint8_t cksum_mask;
> +	cmdline_fixed_string_t mode;
> +	cmdline_fixed_string_t proto;
> +	cmdline_fixed_string_t hwsw;
>  	uint8_t port_id;
>  };
> 
>  static void
> -cmd_tx_cksum_set_parsed(void *parsed_result,
> +cmd_tx_cksum_parsed(void *parsed_result,
>  		       __attribute__((unused)) struct cmdline *cl,
>  		       __attribute__((unused)) void *data)  {
> -	struct cmd_tx_cksum_set_result *res = parsed_result;
> +	struct cmd_tx_cksum_result *res = parsed_result;
> +	int hw = 0;
> +	uint16_t ol_flags, mask = 0;
> +	struct rte_eth_dev_info dev_info;
> +
> +	if (port_id_is_invalid(res->port_id)) {
> +		printf("invalid port %d\n", res->port_id);
> +		return;
> +	}
> 
> -	tx_cksum_set(res->port_id, res->cksum_mask);
> +	if (!strcmp(res->mode, "set")) {
> +
> +		if (!strcmp(res->hwsw, "hw"))
> +			hw = 1;
> +
> +		if (!strcmp(res->proto, "ip")) {
> +			mask = TESTPMD_TX_OFFLOAD_IP_CKSUM;
> +		} else if (!strcmp(res->proto, "udp")) {
> +			mask = TESTPMD_TX_OFFLOAD_UDP_CKSUM;
> +		} else if (!strcmp(res->proto, "tcp")) {
> +			mask = TESTPMD_TX_OFFLOAD_TCP_CKSUM;
> +		} else if (!strcmp(res->proto, "sctp")) {
> +			mask = TESTPMD_TX_OFFLOAD_SCTP_CKSUM;
> +		} else if (!strcmp(res->proto, "vxlan")) {
> +			mask = TESTPMD_TX_OFFLOAD_VXLAN_CKSUM;
> +		}
> +
> +		if (hw)
> +			ports[res->port_id].tx_ol_flags |= mask;
> +		else
> +			ports[res->port_id].tx_ol_flags &= (~mask);
> +	}
> +
> +	ol_flags = ports[res->port_id].tx_ol_flags;
> +	printf("IP checksum offload is %s\n",
> +		(ol_flags & TESTPMD_TX_OFFLOAD_IP_CKSUM) ? "hw" : "sw");
> +	printf("UDP checksum offload is %s\n",
> +		(ol_flags & TESTPMD_TX_OFFLOAD_UDP_CKSUM) ? "hw" :
> "sw");
> +	printf("TCP checksum offload is %s\n",
> +		(ol_flags & TESTPMD_TX_OFFLOAD_TCP_CKSUM) ? "hw" : "sw");
> +	printf("SCTP checksum offload is %s\n",
> +		(ol_flags & TESTPMD_TX_OFFLOAD_SCTP_CKSUM) ? "hw" :
> "sw");
> +	printf("VxLAN checksum offload is %s\n",
> +		(ol_flags & TESTPMD_TX_OFFLOAD_VXLAN_CKSUM) ? "hw" :
> "sw");
> +
> +	/* display warnings if configuration is not supported by the NIC */
> +	rte_eth_dev_info_get(res->port_id, &dev_info);
> +	if ((ol_flags & TESTPMD_TX_OFFLOAD_IP_CKSUM) &&
> +		(dev_info.tx_offload_capa & DEV_TX_OFFLOAD_IPV4_CKSUM)
> == 0) {
> +		printf("Warning: hardware IP checksum enabled but not "
> +			"supported by port %d\n", res->port_id);
> +	}
> +	if ((ol_flags & TESTPMD_TX_OFFLOAD_UDP_CKSUM) &&
> +		(dev_info.tx_offload_capa & DEV_TX_OFFLOAD_UDP_CKSUM)
> == 0) {
> +		printf("Warning: hardware UDP checksum enabled but not "
> +			"supported by port %d\n", res->port_id);
> +	}
> +	if ((ol_flags & TESTPMD_TX_OFFLOAD_TCP_CKSUM) &&
> +		(dev_info.tx_offload_capa & DEV_TX_OFFLOAD_TCP_CKSUM) ==
> 0) {
> +		printf("Warning: hardware TCP checksum enabled but not "
> +			"supported by port %d\n", res->port_id);
> +	}
> +	if ((ol_flags & TESTPMD_TX_OFFLOAD_SCTP_CKSUM) &&
> +		(dev_info.tx_offload_capa & DEV_TX_OFFLOAD_SCTP_CKSUM)
> == 0) {
> +		printf("Warning: hardware SCTP checksum enabled but not "
> +			"supported by port %d\n", res->port_id);
> +	}
>  }
> 
> -cmdline_parse_token_string_t cmd_tx_cksum_set_tx_cksum =
> -	TOKEN_STRING_INITIALIZER(struct cmd_tx_cksum_set_result,
> +cmdline_parse_token_string_t cmd_tx_cksum_tx_cksum =
> +	TOKEN_STRING_INITIALIZER(struct cmd_tx_cksum_result,
>  				tx_cksum, "tx_checksum");
> -cmdline_parse_token_string_t cmd_tx_cksum_set_set =
> -	TOKEN_STRING_INITIALIZER(struct cmd_tx_cksum_set_result,
> -				set, "set");
> -cmdline_parse_token_num_t cmd_tx_cksum_set_cksum_mask =
> -	TOKEN_NUM_INITIALIZER(struct cmd_tx_cksum_set_result,
> -				cksum_mask, UINT8);
> -cmdline_parse_token_num_t cmd_tx_cksum_set_portid =
> -	TOKEN_NUM_INITIALIZER(struct cmd_tx_cksum_set_result,
> +cmdline_parse_token_string_t cmd_tx_cksum_mode =
> +	TOKEN_STRING_INITIALIZER(struct cmd_tx_cksum_result,
> +				mode, "set");
> +cmdline_parse_token_string_t cmd_tx_cksum_proto =
> +	TOKEN_STRING_INITIALIZER(struct cmd_tx_cksum_result,
> +				proto, "ip#tcp#udp#sctp#vxlan");
> +cmdline_parse_token_string_t cmd_tx_cksum_hwsw =
> +	TOKEN_STRING_INITIALIZER(struct cmd_tx_cksum_result,
> +				hwsw, "hw#sw");
> +cmdline_parse_token_num_t cmd_tx_cksum_portid =
> +	TOKEN_NUM_INITIALIZER(struct cmd_tx_cksum_result,
>  				port_id, UINT8);
> 
>  cmdline_parse_inst_t cmd_tx_cksum_set = {
> -	.f = cmd_tx_cksum_set_parsed,
> +	.f = cmd_tx_cksum_parsed,
> +	.data = NULL,
> +	.help_str = "enable/disable hardware calculation of L3/L4 checksum
> when "
> +		"using csum forward engine: tx_cksum set
> ip|tcp|udp|sctp|vxlan hw|sw <port>",
> +	.tokens = {
> +		(void *)&cmd_tx_cksum_tx_cksum,
> +		(void *)&cmd_tx_cksum_mode,
> +		(void *)&cmd_tx_cksum_proto,
> +		(void *)&cmd_tx_cksum_hwsw,
> +		(void *)&cmd_tx_cksum_portid,
> +		NULL,
> +	},
> +};
> +
> +cmdline_parse_token_string_t cmd_tx_cksum_mode_show =
> +	TOKEN_STRING_INITIALIZER(struct cmd_tx_cksum_result,
> +				mode, "show");
> +
> +cmdline_parse_inst_t cmd_tx_cksum_show = {
> +	.f = cmd_tx_cksum_parsed,
>  	.data = NULL,
> -	.help_str = "enable hardware insertion of L3/L4checksum with a given "
> -	"mask in packets sent on a port, the bit mapping is given as, Bit 0 for ip, "
> -	"Bit 1 for UDP, Bit 2 for TCP, Bit 3 for SCTP, Bit 4 for inner ip, "
> -	"Bit 5 for inner UDP, Bit 6 for inner TCP, Bit 7 for inner SCTP",
> +	.help_str = "show checksum offload configuration: tx_cksum show
> +<port>",
>  	.tokens = {
> -		(void *)&cmd_tx_cksum_set_tx_cksum,
> -		(void *)&cmd_tx_cksum_set_set,
> -		(void *)&cmd_tx_cksum_set_cksum_mask,
> -		(void *)&cmd_tx_cksum_set_portid,
> +		(void *)&cmd_tx_cksum_tx_cksum,
> +		(void *)&cmd_tx_cksum_mode_show,
> +		(void *)&cmd_tx_cksum_portid,
>  		NULL,
>  	},
>  };
> @@ -7796,6 +7874,7 @@ cmdline_parse_ctx_t main_ctx[] = {
>  	(cmdline_parse_inst_t *)&cmd_tx_vlan_reset,
>  	(cmdline_parse_inst_t *)&cmd_tx_vlan_set_pvid,
>  	(cmdline_parse_inst_t *)&cmd_tx_cksum_set,
> +	(cmdline_parse_inst_t *)&cmd_tx_cksum_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, diff --git
> a/app/test-pmd/config.c b/app/test-pmd/config.c index 34b6fdb..16d62ab
> 100644
> --- a/app/test-pmd/config.c
> +++ b/app/test-pmd/config.c
> @@ -1744,17 +1744,6 @@ set_qmap(portid_t port_id, uint8_t is_rx, uint16_t
> queue_id, uint8_t map_value)  }
> 
>  void
> -tx_cksum_set(portid_t port_id, uint64_t ol_flags) -{
> -	uint64_t tx_ol_flags;
> -	if (port_id_is_invalid(port_id))
> -		return;
> -	/* Clear last 8 bits and then set L3/4 checksum mask again */
> -	tx_ol_flags = ports[port_id].tx_ol_flags & (~0x0FFull);
> -	ports[port_id].tx_ol_flags = ((ol_flags & 0xff) | tx_ol_flags);
> -}
> -
> -void
>  fdir_add_signature_filter(portid_t port_id, uint8_t queue_id,
>  			  struct rte_fdir_filter *fdir_filter)  { diff --git a/app/test-
> pmd/csumonly.c b/app/test-pmd/csumonly.c index 743094a..dda5d9e 100644
> --- a/app/test-pmd/csumonly.c
> +++ b/app/test-pmd/csumonly.c
> @@ -73,13 +73,19 @@
>  #include <rte_string_fns.h>
>  #include "testpmd.h"
> 
> -
> -
>  #define IP_DEFTTL  64   /* from RFC 1340. */
>  #define IP_VERSION 0x40
>  #define IP_HDRLEN  0x05 /* default IP header length == five 32-bits words. */
> #define IP_VHL_DEF (IP_VERSION | IP_HDRLEN)
> 
> +/* we cannot use htons() from arpa/inet.h due to name conflicts, and we
> + * cannot use rte_cpu_to_be_16() on a constant in a switch/case */ #if
> +__BYTE_ORDER == __LITTLE_ENDIAN #define _htons(x) ((uint16_t)((((x) &
> +0x00ffU) << 8) | (((x) & 0xff00U) >> 8))) #else #define _htons(x) (x)
> +#endif
> +
>  static inline uint16_t
>  get_16b_sum(uint16_t *ptr16, uint32_t nr)  { @@ -112,7 +118,7 @@
> get_ipv4_cksum(struct ipv4_hdr *ipv4_hdr)
> 
> 
>  static inline uint16_t
> -get_ipv4_psd_sum (struct ipv4_hdr * ip_hdr)
> +get_ipv4_psd_sum(struct ipv4_hdr *ip_hdr)
>  {
>  	/* Pseudo Header for IPv4/UDP/TCP checksum */
>  	union ipv4_psd_header {
> @@ -136,7 +142,7 @@ get_ipv4_psd_sum (struct ipv4_hdr * ip_hdr)  }
> 
>  static inline uint16_t
> -get_ipv6_psd_sum (struct ipv6_hdr * ip_hdr)
> +get_ipv6_psd_sum(struct ipv6_hdr *ip_hdr)
>  {
>  	/* Pseudo Header for IPv6/UDP/TCP checksum */
>  	union ipv6_psd_header {
> @@ -158,6 +164,15 @@ get_ipv6_psd_sum (struct ipv6_hdr * ip_hdr)
>  	return get_16b_sum(psd_hdr.u16_arr, sizeof(psd_hdr));  }
> 
> +static uint16_t
> +get_psd_sum(void *l3_hdr, uint16_t ethertype) {
> +	if (ethertype == _htons(ETHER_TYPE_IPv4))
> +		return get_ipv4_psd_sum(l3_hdr);
> +	else /* assume ethertype == ETHER_TYPE_IPv6 */
> +		return get_ipv6_psd_sum(l3_hdr);
> +}
> +
>  static inline uint16_t
>  get_ipv4_udptcp_checksum(struct ipv4_hdr *ipv4_hdr, uint16_t *l4_hdr)  { @@ -
> 174,7 +189,6 @@ get_ipv4_udptcp_checksum(struct ipv4_hdr *ipv4_hdr,
> uint16_t *l4_hdr)
>  	if (cksum == 0)
>  		cksum = 0xffff;
>  	return (uint16_t)cksum;
> -
>  }
> 
>  static inline uint16_t
> @@ -196,48 +210,218 @@ get_ipv6_udptcp_checksum(struct ipv6_hdr
> *ipv6_hdr, uint16_t *l4_hdr)
>  	return (uint16_t)cksum;
>  }
> 
> +static uint16_t
> +get_udptcp_checksum(void *l3_hdr, void *l4_hdr, uint16_t ethertype) {
> +	if (ethertype == _htons(ETHER_TYPE_IPv4))
> +		return get_ipv4_udptcp_checksum(l3_hdr, l4_hdr);
> +	else /* assume ethertype == ETHER_TYPE_IPv6 */
> +		return get_ipv6_udptcp_checksum(l3_hdr, l4_hdr); }
> 
>  /*
> - * Forwarding of packets. Change the checksum field with HW or SW methods
> - * The HW/SW method selection depends on the ol_flags on every packet
> + * Parse an ethernet header to fill the ethertype, l2_len, l3_len and
> + * ipproto. This function is able to recognize IPv4/IPv6 with one
> +optional vlan
> + * header.
> + */
> +static void
> +parse_ethernet(struct ether_hdr *eth_hdr, uint16_t *ethertype, uint16_t
> *l2_len,
> +	uint16_t *l3_len, uint8_t *l4_proto)
> +{
> +	struct ipv4_hdr *ipv4_hdr;
> +	struct ipv6_hdr *ipv6_hdr;
> +
> +	*l2_len = sizeof(struct ether_hdr);
> +	*ethertype = eth_hdr->ether_type;
> +
> +	if (*ethertype == _htons(ETHER_TYPE_VLAN)) {
> +		struct vlan_hdr *vlan_hdr = (struct vlan_hdr *)(eth_hdr + 1);
> +
> +		*l2_len  += sizeof(struct vlan_hdr);
> +		*ethertype = vlan_hdr->eth_proto;
> +	}
> +
> +	switch (*ethertype) {
> +	case _htons(ETHER_TYPE_IPv4):
> +		ipv4_hdr = (struct ipv4_hdr *) ((char *)eth_hdr + *l2_len);
> +		*l3_len = (ipv4_hdr->version_ihl & 0x0f) * 4;
> +		*l4_proto = ipv4_hdr->next_proto_id;
> +		break;
> +	case _htons(ETHER_TYPE_IPv6):
> +		ipv6_hdr = (struct ipv6_hdr *) ((char *)eth_hdr + *l2_len);
> +		*l3_len = sizeof(struct ipv6_hdr) ;
> +		*l4_proto = ipv6_hdr->proto;
> +		break;
> +	default:
> +		*l3_len = 0;
> +		*l4_proto = 0;
> +		break;
> +	}
> +}
> +
> +/* 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 process_inner_cksums(void *l3_hdr, uint16_t ethertype,
> +uint16_t l3_len,
> +	uint8_t l4_proto, uint16_t testpmd_ol_flags) {
> +	struct ipv4_hdr *ipv4_hdr = l3_hdr;
> +	struct udp_hdr *udp_hdr;
> +	struct tcp_hdr *tcp_hdr;
> +	struct sctp_hdr *sctp_hdr;
> +	uint64_t ol_flags = 0;
> +
> +	if (ethertype == _htons(ETHER_TYPE_IPv4)) {
> +		ipv4_hdr = l3_hdr;
> +		ipv4_hdr->hdr_checksum = 0;
> +
> +		if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_IP_CKSUM)
> +			ol_flags |= PKT_TX_IP_CKSUM;
> +		else
> +			ipv4_hdr->hdr_checksum = get_ipv4_cksum(ipv4_hdr);
> +
> +	}
> +	else if (ethertype != _htons(ETHER_TYPE_IPv6))
> +		return 0; /* packet type not supported nothing to do */
> +
> +	if (l4_proto == IPPROTO_UDP) {
> +		udp_hdr = (struct udp_hdr *)((char *)l3_hdr + l3_len);
> +		/* do not recalculate udp cksum if it was 0 */
> +		if (udp_hdr->dgram_cksum != 0) {
> +			udp_hdr->dgram_cksum = 0;
> +			if (testpmd_ol_flags &
> TESTPMD_TX_OFFLOAD_UDP_CKSUM) {
> +				ol_flags |= PKT_TX_UDP_CKSUM;
> +				udp_hdr->dgram_cksum = get_psd_sum(l3_hdr,
> +					ethertype);
> +			}
> +			else {
> +				udp_hdr->dgram_cksum =
> +					get_udptcp_checksum(l3_hdr, udp_hdr,
> +						ethertype);
> +			}
> +		}
> +	}
> +	else if (l4_proto == IPPROTO_TCP) {
> +		tcp_hdr = (struct tcp_hdr *)((char *)l3_hdr + l3_len);
> +		tcp_hdr->cksum = 0;
> +		if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_TCP_CKSUM) {
> +			ol_flags |= PKT_TX_TCP_CKSUM;
> +			tcp_hdr->cksum = get_psd_sum(l3_hdr, ethertype);
> +		}
> +		else {
> +			tcp_hdr->cksum =
> +				get_udptcp_checksum(l3_hdr, tcp_hdr,
> ethertype);
> +		}
> +	}
> +	else if (l4_proto == IPPROTO_SCTP) {
> +		sctp_hdr = (struct sctp_hdr *)((char *)l3_hdr + l3_len);
> +		sctp_hdr->cksum = 0;
> +		/* sctp payload must be a multiple of 4 to be
> +		 * offloaded */
> +		if ((testpmd_ol_flags & TESTPMD_TX_OFFLOAD_SCTP_CKSUM)
> &&
> +			((ipv4_hdr->total_length & 0x3) == 0)) {
> +			ol_flags |= PKT_TX_SCTP_CKSUM;
> +		}
> +		else {
> +			/* XXX implement CRC32c, example available in
> +			 * RFC3309 */
> +		}
> +	}
> +
> +	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 */
> +static uint64_t
> +process_outer_cksums(void *outer_l3_hdr, uint16_t outer_ethertype,
> +	uint16_t outer_l3_len, uint16_t testpmd_ol_flags) {
> +	struct ipv4_hdr *ipv4_hdr = outer_l3_hdr;
> +	struct ipv6_hdr *ipv6_hdr = outer_l3_hdr;
> +	struct udp_hdr *udp_hdr;
> +	uint64_t ol_flags = 0;
> +
> +	if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_VXLAN_CKSUM)
> +		ol_flags |= PKT_TX_VXLAN_CKSUM;
> +
> +	if (outer_ethertype == _htons(ETHER_TYPE_IPv4)) {
> +		ipv4_hdr->hdr_checksum = 0;
> +
> +		if ((testpmd_ol_flags & TESTPMD_TX_OFFLOAD_VXLAN_CKSUM)
> == 0)
> +			ipv4_hdr->hdr_checksum = get_ipv4_cksum(ipv4_hdr);
> +	}

As I mentioned, we should use TESTPMD_TX_OFFLOAD_IP_CKSUM instead of using TESTPMD_TX_OFFLOAD_VXLAN_CKSUM flag to check if we need to set outer IP checksum offload.
In other words, even if VXLAN packet, outer IP TX checksum offload is also needed if  TESTPMD_TX_OFFLOAD_IP_CKSUM is set.

> +	udp_hdr = (struct udp_hdr *)((char *)outer_l3_hdr + outer_l3_len);
> +	/* do not recalculate udp cksum if it was 0 */
> +	if (udp_hdr->dgram_cksum != 0) {
> +		udp_hdr->dgram_cksum = 0;
> +		if ((testpmd_ol_flags & TESTPMD_TX_OFFLOAD_VXLAN_CKSUM)
> == 0) {
> +			if (outer_ethertype == _htons(ETHER_TYPE_IPv4))
> +				udp_hdr->dgram_cksum =
> +					get_ipv4_udptcp_checksum(ipv4_hdr,
> +						(uint16_t *)udp_hdr);
> +			else
> +				udp_hdr->dgram_cksum =
> +					get_ipv6_udptcp_checksum(ipv6_hdr,
> +						(uint16_t *)udp_hdr);
> +		}
> +	}
> +
> +	return ol_flags;
> +}
> +
> +/*
> + * Receive a burst of packets, and for supported packet types:
> + *  - modify the IPs
> + *  - reprocess the checksum in SW or HW, depending on testpmd command line
> + *    configuration
> + * Then packets are transmitted on the output port.
> + *
> + * Supported packets are:
> + *   Ether / (vlan) / IP|IP6 / UDP|TCP|SCTP .
> + *   Ether / (vlan) / IP|IP6 / UDP / VxLAN / Ether / IP|IP6 / UDP|TCP|SCTP
> + *
> + * The network parser supposes that the packet is contiguous, which may
> + * not be the case in real life.
>   */
>  static void
>  pkt_burst_checksum_forward(struct fwd_stream *fs)  {
> -	struct rte_mbuf  *pkts_burst[MAX_PKT_BURST];
> -	struct rte_port  *txp;
> -	struct rte_mbuf  *mb;
> +	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
> +	struct rte_port *txp;
> +	struct rte_mbuf *m;
>  	struct ether_hdr *eth_hdr;
> -	struct ipv4_hdr  *ipv4_hdr;
> -	struct ether_hdr *inner_eth_hdr;
> -	struct ipv4_hdr  *inner_ipv4_hdr = NULL;
> -	struct ipv6_hdr  *ipv6_hdr;
> -	struct ipv6_hdr  *inner_ipv6_hdr = NULL;
> -	struct udp_hdr   *udp_hdr;
> -	struct udp_hdr   *inner_udp_hdr;
> -	struct tcp_hdr   *tcp_hdr;
> -	struct tcp_hdr   *inner_tcp_hdr;
> -	struct sctp_hdr  *sctp_hdr;
> -	struct sctp_hdr  *inner_sctp_hdr;
> -
> +	void *l3_hdr = NULL, *outer_l3_hdr = NULL; /* can be IPv4 or IPv6 */
> +	struct udp_hdr *udp_hdr;
>  	uint16_t nb_rx;
>  	uint16_t nb_tx;
>  	uint16_t i;
>  	uint64_t ol_flags;
> -	uint64_t pkt_ol_flags;
> -	uint64_t tx_ol_flags;
> -	uint16_t l4_proto;
> -	uint16_t inner_l4_proto = 0;
> -	uint16_t eth_type;
> -	uint8_t  l2_len;
> -	uint8_t  l3_len;
> -	uint8_t  inner_l2_len = 0;
> -	uint8_t  inner_l3_len = 0;
> -
> +	uint16_t testpmd_ol_flags;
> +	uint8_t l4_proto;
> +	uint16_t ethertype = 0, outer_ethertype = 0;
> +	uint16_t  l2_len = 0, l3_len = 0, outer_l2_len = 0, outer_l3_len = 0;
> +	int tunnel = 0;
>  	uint32_t rx_bad_ip_csum;
>  	uint32_t rx_bad_l4_csum;
> -	uint8_t  ipv4_tunnel;
> -	uint8_t  ipv6_tunnel;
> 
>  #ifdef RTE_TEST_PMD_RECORD_CORE_CYCLES
>  	uint64_t start_tsc;
> @@ -249,9 +433,7 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
>  	start_tsc = rte_rdtsc();
>  #endif
> 
> -	/*
> -	 * Receive a burst of packets and forward them.
> -	 */
> +	/* receive a burst of packet */
>  	nb_rx = rte_eth_rx_burst(fs->rx_port, fs->rx_queue, pkts_burst,
>  				 nb_pkt_per_burst);
>  	if (unlikely(nb_rx == 0))
> @@ -265,348 +447,107 @@ pkt_burst_checksum_forward(struct fwd_stream
> *fs)
>  	rx_bad_l4_csum = 0;
> 
>  	txp = &ports[fs->tx_port];
> -	tx_ol_flags = txp->tx_ol_flags;
> +	testpmd_ol_flags = txp->tx_ol_flags;
> 
>  	for (i = 0; i < nb_rx; i++) {
> 
> -		mb = pkts_burst[i];
> -		l2_len  = sizeof(struct ether_hdr);
> -		pkt_ol_flags = mb->ol_flags;
> -		ol_flags = (pkt_ol_flags & (~PKT_TX_L4_MASK));
> -		ipv4_tunnel = (pkt_ol_flags & PKT_RX_TUNNEL_IPV4_HDR) ?
> -				1 : 0;
> -		ipv6_tunnel = (pkt_ol_flags & PKT_RX_TUNNEL_IPV6_HDR) ?
> -				1 : 0;
> -		eth_hdr = rte_pktmbuf_mtod(mb, struct ether_hdr *);
> -		eth_type = rte_be_to_cpu_16(eth_hdr->ether_type);
> -		if (eth_type == ETHER_TYPE_VLAN) {
> -			/* Only allow single VLAN label here */
> -			l2_len  += sizeof(struct vlan_hdr);
> -			 eth_type = rte_be_to_cpu_16(*(uint16_t *)
> -				((uintptr_t)&eth_hdr->ether_type +
> -				sizeof(struct vlan_hdr)));
> +		ol_flags = 0;
> +		tunnel = 0;
> +		m = pkts_burst[i];
> +
> +		/* 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);
> +
> +		/* step 1: dissect packet, parsing optional vlan, ip4/ip6, vxlan
> +		 * and inner headers */
> +
> +		eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
> +		parse_ethernet(eth_hdr, &ethertype, &l2_len, &l3_len,
> &l4_proto);
> +		l3_hdr = (char *)eth_hdr + l2_len;
> +
> +		/* check if it's a supported tunnel (only vxlan for now) */
> +		if (l4_proto == IPPROTO_UDP) {
> +			udp_hdr = (struct udp_hdr *)((char *)l3_hdr + l3_len);
> +
> +			/* currently, this flag is set by i40e only if the
> +			 * packet is vxlan */
> +			if (((m->ol_flags & PKT_RX_TUNNEL_IPV4_HDR) ||
> +					(m->ol_flags &
> PKT_RX_TUNNEL_IPV6_HDR)))
> +				tunnel = 1;
> +			/* else check udp destination port, 4789 is the default
> +			 * vxlan port (rfc7348) */
> +			else if (udp_hdr->dst_port == _htons(4789))
> +				tunnel = 1;
> +
> +			if (tunnel == 1) {
> +				outer_ethertype = ethertype;
> +				outer_l2_len = l2_len;
> +				outer_l3_len = l3_len;
> +				outer_l3_hdr = l3_hdr;
> +
> +				eth_hdr = (struct ether_hdr *)((char *)udp_hdr +
> +					sizeof(struct udp_hdr) +
> +					sizeof(struct vxlan_hdr));
> +
> +				parse_ethernet(eth_hdr, &ethertype, &l2_len,
> +					&l3_len, &l4_proto);
> +				l3_hdr = (char *)eth_hdr + l2_len;
> +			}
>  		}
> 
> -		/* Update the L3/L4 checksum error packet count  */
> -		rx_bad_ip_csum += (uint16_t) ((pkt_ol_flags &
> PKT_RX_IP_CKSUM_BAD) != 0);
> -		rx_bad_l4_csum += (uint16_t) ((pkt_ol_flags &
> PKT_RX_L4_CKSUM_BAD) != 0);
> -
> -		/*
> -		 * Try to figure out L3 packet type by SW.
> -		 */
> -		if ((pkt_ol_flags & (PKT_RX_IPV4_HDR | PKT_RX_IPV4_HDR_EXT
> |
> -				PKT_RX_IPV6_HDR | PKT_RX_IPV6_HDR_EXT))
> == 0) {
> -			if (eth_type == ETHER_TYPE_IPv4)
> -				pkt_ol_flags |= PKT_RX_IPV4_HDR;
> -			else if (eth_type == ETHER_TYPE_IPv6)
> -				pkt_ol_flags |= PKT_RX_IPV6_HDR;
> -		}
> +		/* step 2: change all source IPs (v4 or v6) so we need
> +		 * to recompute the chksums even if they were correct */
> 
> -		/*
> -		 * Simplify the protocol parsing
> -		 * Assuming the incoming packets format as
> -		 *      Ethernet2 + optional single VLAN
> -		 *      + ipv4 or ipv6
> -		 *      + udp or tcp or sctp or others
> -		 */
> -		if (pkt_ol_flags & (PKT_RX_IPV4_HDR |
> PKT_RX_TUNNEL_IPV4_HDR)) {
> +		change_ip_addresses(l3_hdr, ethertype);
> +		if (tunnel == 1)
> +			change_ip_addresses(outer_l3_hdr, outer_ethertype);
> 
> -			/* Do not support ipv4 option field */
> -			l3_len = sizeof(struct ipv4_hdr) ;
> +		/* step 3: depending on user command line configuration,
> +		 * recompute checksum either in software or flag the
> +		 * mbuf to offload the calculation to the NIC */
> 
> -			ipv4_hdr = (struct ipv4_hdr *) (rte_pktmbuf_mtod(mb,
> -					unsigned char *) + l2_len);
> +		/* process checksums of inner headers first */
> +		ol_flags |= process_inner_cksums(l3_hdr, ethertype,
> +			l3_len, l4_proto, testpmd_ol_flags);
> -			l4_proto = ipv4_hdr->next_proto_id;
> +		/* 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 (tunnel == 1) {
> +			ol_flags |= process_outer_cksums(outer_l3_hdr,
> +				outer_ethertype, outer_l3_len,
> testpmd_ol_flags);
> +		}
> 
> -			/* Do not delete, this is required by HW*/
> -			ipv4_hdr->hdr_checksum = 0;
> +		/* step 4: fill the mbuf meta data (flags and header lengths) */
> 
> -			if (tx_ol_flags & TESTPMD_TX_OFFLOAD_IP_CKSUM) {
> -				/* HW checksum */
> -				ol_flags |= PKT_TX_IP_CKSUM;
> +		if (tunnel == 1) {
> +			if (testpmd_ol_flags &
> TESTPMD_TX_OFFLOAD_VXLAN_CKSUM) {
> +				m->l2_len = outer_l2_len;
> +				m->l3_len = outer_l3_len;
> +				m->inner_l2_len = l2_len;
> +				m->inner_l3_len = l3_len;
>  			}
>  			else {
> -				ol_flags |= PKT_TX_IPV4;
> -				/* SW checksum calculation */
> -				ipv4_hdr->src_addr++;
> -				ipv4_hdr->hdr_checksum =
> get_ipv4_cksum(ipv4_hdr);
> +				/* if we don't do vxlan cksum in hw,
> +				   outer checksum will be wrong because
> +				   we changed the ip, but it shows that
> +				   we can process the inner header cksum
> +				   in the nic */
> +				m->l2_len = outer_l2_len + outer_l3_len +
> +					sizeof(struct udp_hdr) +
> +					sizeof(struct vxlan_hdr) + l2_len;
> +				m->l3_len = l3_len;
>  			}
> -
> -			if (l4_proto == IPPROTO_UDP) {
> -				udp_hdr = (struct udp_hdr*)
> (rte_pktmbuf_mtod(mb,
> -						unsigned char *) + l2_len +
> l3_len);
> -				if (tx_ol_flags &
> TESTPMD_TX_OFFLOAD_UDP_CKSUM) {
> -					/* HW Offload */
> -					ol_flags |= PKT_TX_UDP_CKSUM;
> -					if (ipv4_tunnel)
> -						udp_hdr->dgram_cksum = 0;
> -					else
> -						/* Pseudo header sum need be
> set properly */
> -						udp_hdr->dgram_cksum =
> -
> 	get_ipv4_psd_sum(ipv4_hdr);
> -				}
> -				else {
> -					/* SW Implementation, clear checksum
> field first */
> -					udp_hdr->dgram_cksum = 0;
> -					udp_hdr->dgram_cksum =
> get_ipv4_udptcp_checksum(ipv4_hdr,
> -
> 	(uint16_t *)udp_hdr);
> -				}
> -
> -				if (ipv4_tunnel) {
> -
> -					uint16_t len;
> -
> -					/* Check if inner L3/L4 checkum flag is
> set */
> -					if (tx_ol_flags &
> TESTPMD_TX_OFFLOAD_INNER_CKSUM_MASK)
> -						ol_flags |=
> PKT_TX_VXLAN_CKSUM;
> -
> -					inner_l2_len  = sizeof(struct ether_hdr);
> -					inner_eth_hdr = (struct ether_hdr *)
> (rte_pktmbuf_mtod(mb,
> -								unsigned char
> *) + l2_len + l3_len
> -								 +
> ETHER_VXLAN_HLEN);
> -
> -					eth_type =
> rte_be_to_cpu_16(inner_eth_hdr->ether_type);
> -					if (eth_type == ETHER_TYPE_VLAN) {
> -						inner_l2_len += sizeof(struct
> vlan_hdr);
> -						eth_type =
> rte_be_to_cpu_16(*(uint16_t *)
> -							((uintptr_t)&eth_hdr-
> >ether_type +
> -								sizeof(struct
> vlan_hdr)));
> -					}
> -
> -					len = l2_len + l3_len +
> ETHER_VXLAN_HLEN + inner_l2_len;
> -					if (eth_type == ETHER_TYPE_IPv4) {
> -						inner_l3_len = sizeof(struct
> ipv4_hdr);
> -						inner_ipv4_hdr = (struct
> ipv4_hdr *) (rte_pktmbuf_mtod(mb,
> -								unsigned char
> *) + len);
> -						inner_l4_proto =
> inner_ipv4_hdr->next_proto_id;
> -
> -						if (tx_ol_flags &
> TESTPMD_TX_OFFLOAD_INNER_IP_CKSUM) {
> -
> -							/* Do not delete, this is
> required by HW*/
> -							inner_ipv4_hdr-
> >hdr_checksum = 0;
> -							ol_flags |=
> PKT_TX_IPV4_CSUM;
> -						}
> -
> -					} else if (eth_type ==
> ETHER_TYPE_IPv6) {
> -						inner_l3_len = sizeof(struct
> ipv6_hdr);
> -						inner_ipv6_hdr = (struct
> ipv6_hdr *) (rte_pktmbuf_mtod(mb,
> -								unsigned char
> *) + len);
> -						inner_l4_proto =
> inner_ipv6_hdr->proto;
> -					}
> -					if ((inner_l4_proto == IPPROTO_UDP)
> &&
> -						(tx_ol_flags &
> TESTPMD_TX_OFFLOAD_INNER_UDP_CKSUM)) {
> -
> -						/* HW Offload */
> -						ol_flags |=
> PKT_TX_UDP_CKSUM;
> -						inner_udp_hdr = (struct
> udp_hdr *) (rte_pktmbuf_mtod(mb,
> -								unsigned char
> *) + len + inner_l3_len);
> -						if (eth_type ==
> ETHER_TYPE_IPv4)
> -							inner_udp_hdr-
> >dgram_cksum = get_ipv4_psd_sum(inner_ipv4_hdr);
> -						else if (eth_type ==
> ETHER_TYPE_IPv6)
> -							inner_udp_hdr-
> >dgram_cksum = get_ipv6_psd_sum(inner_ipv6_hdr);
> -
> -					} else if ((inner_l4_proto ==
> IPPROTO_TCP) &&
> -						(tx_ol_flags &
> TESTPMD_TX_OFFLOAD_INNER_TCP_CKSUM)) {
> -						/* HW Offload */
> -						ol_flags |=
> PKT_TX_TCP_CKSUM;
> -						inner_tcp_hdr = (struct tcp_hdr
> *) (rte_pktmbuf_mtod(mb,
> -								unsigned char
> *) + len + inner_l3_len);
> -						if (eth_type ==
> ETHER_TYPE_IPv4)
> -							inner_tcp_hdr->cksum
> = get_ipv4_psd_sum(inner_ipv4_hdr);
> -						else if (eth_type ==
> ETHER_TYPE_IPv6)
> -							inner_tcp_hdr->cksum
> = get_ipv6_psd_sum(inner_ipv6_hdr);
> -					} else if ((inner_l4_proto ==
> IPPROTO_SCTP) &&
> -						(tx_ol_flags &
> TESTPMD_TX_OFFLOAD_INNER_SCTP_CKSUM)) {
> -						/* HW Offload */
> -						ol_flags |=
> PKT_TX_SCTP_CKSUM;
> -						inner_sctp_hdr = (struct
> sctp_hdr *) (rte_pktmbuf_mtod(mb,
> -								unsigned char
> *) + len + inner_l3_len);
> -						inner_sctp_hdr->cksum = 0;
> -					}
> -
> -				}
> -
> -			} else if (l4_proto == IPPROTO_TCP) {
> -				tcp_hdr = (struct tcp_hdr*)
> (rte_pktmbuf_mtod(mb,
> -						unsigned char *) + l2_len +
> l3_len);
> -				if (tx_ol_flags &
> TESTPMD_TX_OFFLOAD_TCP_CKSUM) {
> -					ol_flags |= PKT_TX_TCP_CKSUM;
> -					tcp_hdr->cksum =
> get_ipv4_psd_sum(ipv4_hdr);
> -				}
> -				else {
> -					tcp_hdr->cksum = 0;
> -					tcp_hdr->cksum =
> get_ipv4_udptcp_checksum(ipv4_hdr,
> -							(uint16_t*)tcp_hdr);
> -				}
> -			} else if (l4_proto == IPPROTO_SCTP) {
> -				sctp_hdr = (struct sctp_hdr*)
> (rte_pktmbuf_mtod(mb,
> -						unsigned char *) + l2_len +
> l3_len);
> -
> -				if (tx_ol_flags &
> TESTPMD_TX_OFFLOAD_SCTP_CKSUM) {
> -					ol_flags |= PKT_TX_SCTP_CKSUM;
> -					sctp_hdr->cksum = 0;
> -
> -					/* Sanity check, only number of 4 bytes
> supported */
> -					if ((rte_be_to_cpu_16(ipv4_hdr-
> >total_length) % 4) != 0)
> -						printf("sctp payload must be a
> multiple "
> -							"of 4 bytes for
> checksum offload");
> -				}
> -				else {
> -					sctp_hdr->cksum = 0;
> -					/* CRC32c sample code available in
> RFC3309 */
> -				}
> -			}
> -			/* End of L4 Handling*/
> -		} else if (pkt_ol_flags & (PKT_RX_IPV6_HDR |
> PKT_RX_TUNNEL_IPV6_HDR)) {
> -			ipv6_hdr = (struct ipv6_hdr *) (rte_pktmbuf_mtod(mb,
> -					unsigned char *) + l2_len);
> -			l3_len = sizeof(struct ipv6_hdr) ;
> -			l4_proto = ipv6_hdr->proto;
> -			ol_flags |= PKT_TX_IPV6;
> -
> -			if (l4_proto == IPPROTO_UDP) {
> -				udp_hdr = (struct udp_hdr*)
> (rte_pktmbuf_mtod(mb,
> -						unsigned char *) + l2_len +
> l3_len);
> -				if (tx_ol_flags &
> TESTPMD_TX_OFFLOAD_UDP_CKSUM) {
> -					/* HW Offload */
> -					ol_flags |= PKT_TX_UDP_CKSUM;
> -					if (ipv6_tunnel)
> -						udp_hdr->dgram_cksum = 0;
> -					else
> -						udp_hdr->dgram_cksum =
> -
> 	get_ipv6_psd_sum(ipv6_hdr);
> -				}
> -				else {
> -					/* SW Implementation */
> -					/* checksum field need be clear first */
> -					udp_hdr->dgram_cksum = 0;
> -					udp_hdr->dgram_cksum =
> get_ipv6_udptcp_checksum(ipv6_hdr,
> -								(uint16_t
> *)udp_hdr);
> -				}
> -
> -				if (ipv6_tunnel) {
> -
> -					uint16_t len;
> -
> -					/* Check if inner L3/L4 checksum flag is
> set */
> -					if (tx_ol_flags &
> TESTPMD_TX_OFFLOAD_INNER_CKSUM_MASK)
> -						ol_flags |=
> PKT_TX_VXLAN_CKSUM;
> -
> -					inner_l2_len  = sizeof(struct ether_hdr);
> -					inner_eth_hdr = (struct ether_hdr *)
> (rte_pktmbuf_mtod(mb,
> -						unsigned char *) + l2_len +
> l3_len + ETHER_VXLAN_HLEN);
> -					eth_type =
> rte_be_to_cpu_16(inner_eth_hdr->ether_type);
> -
> -					if (eth_type == ETHER_TYPE_VLAN) {
> -						inner_l2_len += sizeof(struct
> vlan_hdr);
> -						eth_type =
> rte_be_to_cpu_16(*(uint16_t *)
> -							((uintptr_t)&eth_hdr-
> >ether_type +
> -							sizeof(struct
> vlan_hdr)));
> -					}
> -
> -					len = l2_len + l3_len +
> ETHER_VXLAN_HLEN + inner_l2_len;
> -
> -					if (eth_type == ETHER_TYPE_IPv4) {
> -						inner_l3_len = sizeof(struct
> ipv4_hdr);
> -						inner_ipv4_hdr = (struct
> ipv4_hdr *) (rte_pktmbuf_mtod(mb,
> -								unsigned char
> *) + len);
> -						inner_l4_proto =
> inner_ipv4_hdr->next_proto_id;
> -
> -						/* HW offload */
> -						if (tx_ol_flags &
> TESTPMD_TX_OFFLOAD_INNER_IP_CKSUM) {
> -
> -							/* Do not delete, this is
> required by HW*/
> -							inner_ipv4_hdr-
> >hdr_checksum = 0;
> -							ol_flags |=
> PKT_TX_IPV4_CSUM;
> -						}
> -					} else if (eth_type ==
> ETHER_TYPE_IPv6) {
> -						inner_l3_len = sizeof(struct
> ipv6_hdr);
> -						inner_ipv6_hdr = (struct
> ipv6_hdr *) (rte_pktmbuf_mtod(mb,
> -							unsigned char *) + len);
> -						inner_l4_proto =
> inner_ipv6_hdr->proto;
> -					}
> -
> -					if ((inner_l4_proto == IPPROTO_UDP)
> &&
> -						(tx_ol_flags &
> TESTPMD_TX_OFFLOAD_INNER_UDP_CKSUM)) {
> -						inner_udp_hdr = (struct
> udp_hdr *) (rte_pktmbuf_mtod(mb,
> -							unsigned char *) + len
> + inner_l3_len);
> -						/* HW offload */
> -						ol_flags |=
> PKT_TX_UDP_CKSUM;
> -						inner_udp_hdr->dgram_cksum
> = 0;
> -						if (eth_type ==
> ETHER_TYPE_IPv4)
> -							inner_udp_hdr-
> >dgram_cksum = get_ipv4_psd_sum(inner_ipv4_hdr);
> -						else if (eth_type ==
> ETHER_TYPE_IPv6)
> -							inner_udp_hdr-
> >dgram_cksum = get_ipv6_psd_sum(inner_ipv6_hdr);
> -					} else if ((inner_l4_proto ==
> IPPROTO_TCP) &&
> -						(tx_ol_flags &
> TESTPMD_TX_OFFLOAD_INNER_TCP_CKSUM)) {
> -						/* HW offload */
> -						ol_flags |=
> PKT_TX_TCP_CKSUM;
> -						inner_tcp_hdr = (struct tcp_hdr
> *) (rte_pktmbuf_mtod(mb,
> -								unsigned char
> *) + len + inner_l3_len);
> -
> -						if (eth_type ==
> ETHER_TYPE_IPv4)
> -							inner_tcp_hdr->cksum
> = get_ipv4_psd_sum(inner_ipv4_hdr);
> -						else if (eth_type ==
> ETHER_TYPE_IPv6)
> -							inner_tcp_hdr->cksum
> = get_ipv6_psd_sum(inner_ipv6_hdr);
> -
> -					} else if ((inner_l4_proto ==
> IPPROTO_SCTP) &&
> -						(tx_ol_flags &
> TESTPMD_TX_OFFLOAD_INNER_SCTP_CKSUM)) {
> -						/* HW offload */
> -						ol_flags |=
> PKT_TX_SCTP_CKSUM;
> -						inner_sctp_hdr = (struct
> sctp_hdr *) (rte_pktmbuf_mtod(mb,
> -								unsigned char
> *) + len + inner_l3_len);
> -						inner_sctp_hdr->cksum = 0;
> -					}
> -
> -				}
> -
> -			}
> -			else if (l4_proto == IPPROTO_TCP) {
> -				tcp_hdr = (struct tcp_hdr*)
> (rte_pktmbuf_mtod(mb,
> -						unsigned char *) + l2_len +
> l3_len);
> -				if (tx_ol_flags &
> TESTPMD_TX_OFFLOAD_TCP_CKSUM) {
> -					ol_flags |= PKT_TX_TCP_CKSUM;
> -					tcp_hdr->cksum =
> get_ipv6_psd_sum(ipv6_hdr);
> -				}
> -				else {
> -					tcp_hdr->cksum = 0;
> -					tcp_hdr->cksum =
> get_ipv6_udptcp_checksum(ipv6_hdr,
> -							(uint16_t*)tcp_hdr);
> -				}
> -			}
> -			else if (l4_proto == IPPROTO_SCTP) {
> -				sctp_hdr = (struct sctp_hdr*)
> (rte_pktmbuf_mtod(mb,
> -						unsigned char *) + l2_len +
> l3_len);
> -
> -				if (tx_ol_flags &
> TESTPMD_TX_OFFLOAD_SCTP_CKSUM) {
> -					ol_flags |= PKT_TX_SCTP_CKSUM;
> -					sctp_hdr->cksum = 0;
> -					/* Sanity check, only number of 4 bytes
> supported by HW */
> -					if ((rte_be_to_cpu_16(ipv6_hdr-
> >payload_len) % 4) != 0)
> -						printf("sctp payload must be a
> multiple "
> -							"of 4 bytes for
> checksum offload");
> -				}
> -				else {
> -					/* CRC32c sample code available in
> RFC3309 */
> -					sctp_hdr->cksum = 0;
> -				}
> -			} else {
> -				printf("Test flow control for 1G PMD \n");
> -			}
> -			/* End of L6 Handling*/
> -		}
> -		else {
> -			l3_len = 0;
> -			printf("Unhandled packet type: %#hx\n", eth_type);
> +		} else {
> +			/* this is only useful if an offload flag is
> +			 * set, but it does not hurt to fill it in any
> +			 * case */
> +			m->l2_len = l2_len;
> +			m->l3_len = l3_len;
>  		}
> +		m->ol_flags = ol_flags;
> 
> -		/* Combine the packet header write. VLAN is not consider here
> */
> -		mb->l2_len = l2_len;
> -		mb->l3_len = l3_len;
> -		mb->inner_l2_len = inner_l2_len;
> -		mb->inner_l3_len = inner_l3_len;
> -		mb->ol_flags = ol_flags;
>  	}
>  	nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, pkts_burst, nb_rx);
>  	fs->tx_packets += nb_tx;
> @@ -629,7 +570,6 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
> #endif  }
> 
> -
>  struct fwd_engine csum_fwd_engine = {
>  	.fwd_mode_name  = "csum",
>  	.port_fwd_begin = NULL,
> diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h index
> 82af2bd..c753d37 100644
> --- a/app/test-pmd/testpmd.h
> +++ b/app/test-pmd/testpmd.h
> @@ -131,18 +131,11 @@ struct fwd_stream {
>  #define TESTPMD_TX_OFFLOAD_TCP_CKSUM         0x0004
>  /** Offload SCTP checksum in csum forward engine */
>  #define TESTPMD_TX_OFFLOAD_SCTP_CKSUM        0x0008
> -/** Offload inner IP checksum in csum forward engine */
> -#define TESTPMD_TX_OFFLOAD_INNER_IP_CKSUM    0x0010
> -/** Offload inner UDP checksum in csum forward engine */
> -#define TESTPMD_TX_OFFLOAD_INNER_UDP_CKSUM   0x0020
> -/** Offload inner TCP checksum in csum forward engine */
> -#define TESTPMD_TX_OFFLOAD_INNER_TCP_CKSUM   0x0040
> -/** Offload inner SCTP checksum in csum forward engine */ -#define
> TESTPMD_TX_OFFLOAD_INNER_SCTP_CKSUM  0x0080
> -/** Offload inner IP checksum mask */
> -#define TESTPMD_TX_OFFLOAD_INNER_CKSUM_MASK  0x00F0
> +/** Offload VxLAN checksum in csum forward engine */
> +#define TESTPMD_TX_OFFLOAD_VXLAN_CKSUM       0x0010
>  /** Insert VLAN header in forward engine */
> -#define TESTPMD_TX_OFFLOAD_INSERT_VLAN       0x0100
> +#define TESTPMD_TX_OFFLOAD_INSERT_VLAN       0x0020
> +
>  /**
>   * The data structure associated with each port.
>   */
> @@ -510,8 +503,6 @@ void tx_vlan_pvid_set(portid_t port_id, uint16_t vlan_id,
> int on);
> 
>  void set_qmap(portid_t port_id, uint8_t is_rx, uint16_t queue_id, uint8_t
> map_value);
> 
> -void tx_cksum_set(portid_t port_id, uint64_t ol_flags);
> -
>  void set_verbose_level(uint16_t vb_level);  void set_tx_pkt_segments(unsigned
> *seg_lengths, unsigned nb_segs);  void set_nb_pkt_per_burst(uint16_t
> pkt_burst);
> --
> 2.1.0