-----Original Message-----
From: Gregory Etelson <redacted>
Sent: Tuesday, July 27, 2021 21:08
To: dev@dpdk.org
Cc: getelson@nvidia.com; Ajit Khaparde <ajit.khaparde@broadcom.com>;
Olivier Matz [off-list ref]; Andrew Rybchenko
[off-list ref]; Yigit, Ferruh [off-list ref];
Thomas Monjalon [off-list ref]; stable@dpdk.org; Li, Xiaoyun
[off-list ref]
Subject: [PATCH v2] app/testpmd: fix TX checksum calculation for tunnel

TX checksum of a tunnelled packet can be calculated for outer headers only or
for both outer and inner parts. The calculation method is determined by
application.
If TX checksum calculation can be offloaded, hardware ignores existing
checksum value and replaces it with an updated result.
If TX checksum is calculated by a software, existing value must be zeroed first.
The testpmd checksum forwarding engine always zeroed inner checksums.
If inner checksum calculation was offloaded, that header was left with 0
checksum value.
Following outer software checksum calculation produced wrong value.
The patch zeroes inner IPv4 checksum only before software calculation.

Fixes: 51f694dd40f5 ("app/testpmd: rework checksum forward engine")
Cc: stable@dpdk.org

Signed-off-by: Gregory Etelson <redacted>
---
v2:
 remove blank line between Fixes and Cc
 explicitly compare with 0 value in `if ()`
---
 app/test-pmd/csumonly.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/app/test-pmd/csumonly.c b/app/test-pmd/csumonly.c index

0161f72175..bd5ad64a57 100644

--- a/app/test-pmd/csumonly.c
+++ b/app/test-pmd/csumonly.c

@@ -480,17 +480,18 @@ process_inner_cksums(void *l3_hdr, const struct

testpmd_offload_info *info,

 	if (info->ethertype == _htons(RTE_ETHER_TYPE_IPV4)) {
 		ipv4_hdr = l3_hdr;
-		ipv4_hdr->hdr_checksum = 0;

 		ol_flags |= PKT_TX_IPV4;
 		if (info->l4_proto == IPPROTO_TCP && tso_segsz) {
 			ol_flags |= PKT_TX_IP_CKSUM;
 		} else {
-			if (tx_offloads & DEV_TX_OFFLOAD_IPV4_CKSUM)
+			if (tx_offloads & DEV_TX_OFFLOAD_IPV4_CKSUM) {
 				ol_flags |= PKT_TX_IP_CKSUM;
-			else
+			} else if (ipv4_hdr->hdr_checksum != 0) {
+				ipv4_hdr->hdr_checksum = 0;
 				ipv4_hdr->hdr_checksum =
 					rte_ipv4_cksum(ipv4_hdr);
+			}
 		}
 	} else if (info->ethertype == _htons(RTE_ETHER_TYPE_IPV6))
 		ol_flags |= PKT_TX_IPV6;

@@ -501,10 +502,10 @@ process_inner_cksums(void *l3_hdr, const struct

testpmd_offload_info *info,
 		udp_hdr = (struct rte_udp_hdr *)((char *)l3_hdr + info->l3_len);
 		/* do not recalculate udp cksum if it was 0 */
 		if (udp_hdr->dgram_cksum != 0) {
-			udp_hdr->dgram_cksum = 0;
-			if (tx_offloads & DEV_TX_OFFLOAD_UDP_CKSUM)
+			if (tx_offloads & DEV_TX_OFFLOAD_UDP_CKSUM) {
 				ol_flags |= PKT_TX_UDP_CKSUM;
-			else {
+			} else {

+				udp_hdr->dgram_cksum = 0;
 				udp_hdr->dgram_cksum =
 					get_udptcp_checksum(l3_hdr, udp_hdr,
 						info->ethertype);

@@ -514,12 +515,12 @@ process_inner_cksums(void *l3_hdr, const struct

testpmd_offload_info *info,
 			ol_flags |= PKT_TX_UDP_SEG;
 	} else if (info->l4_proto == IPPROTO_TCP) {
 		tcp_hdr = (struct rte_tcp_hdr *)((char *)l3_hdr + info->l3_len);
-		tcp_hdr->cksum = 0;
 		if (tso_segsz)
 			ol_flags |= PKT_TX_TCP_SEG;
-		else if (tx_offloads & DEV_TX_OFFLOAD_TCP_CKSUM)
+		else if (tx_offloads & DEV_TX_OFFLOAD_TCP_CKSUM) {
 			ol_flags |= PKT_TX_TCP_CKSUM;
-		else {
+		} else if (tcp_hdr->cksum != 0) {
+			tcp_hdr->cksum = 0;
 			tcp_hdr->cksum =
 				get_udptcp_checksum(l3_hdr, tcp_hdr,
 					info->ethertype);

@@ -529,13 +530,13 @@ process_inner_cksums(void *l3_hdr, const struct

testpmd_offload_info *info,
 	} else if (info->l4_proto == IPPROTO_SCTP) {
 		sctp_hdr = (struct rte_sctp_hdr *)
 			((char *)l3_hdr + info->l3_len);
-		sctp_hdr->cksum = 0;
 		/* sctp payload must be a multiple of 4 to be
 		 * offloaded */
 		if ((tx_offloads & DEV_TX_OFFLOAD_SCTP_CKSUM) &&
 			((ipv4_hdr->total_length & 0x3) == 0)) {
 			ol_flags |= PKT_TX_SCTP_CKSUM;
-		} else {
+		} else if (sctp_hdr->cksum != 0) {
+			sctp_hdr->cksum = 0;
 			/* XXX implement CRC32c, example available in
 			 * RFC3309 */
 		}
--
2.32.0