In ipsec-secgw wrong SPI number is read from incoming ESP packet. The problem exist inside function inbound_sa_lookup(). The SPI is read from mbuf where the information is stored in big-endian. In low-endian environment the value is erroneous. Fixed by add conversion rte_be_to_cpu_32().
Fixes: d299106e8e31 ("examples/ipsec-secgw: add IPsec sample application") Signed-off-by: Slawomir Mrozowicz <slawomirx.mrozowicz at intel.com> --- examples/ipsec-secgw/sa.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/ipsec-secgw/sa.c b/examples/ipsec-secgw/sa.c index b6260ed..503e345 100644 --- a/examples/ipsec-secgw/sa.c +++ b/examples/ipsec-secgw/sa.c @@ -416,8 +416,8 @@ inbound_sa_lookup(struct sa_ctx *sa_ctx, struct rte_mbuf *pkts[], uint32_t *src, spi; for (i = 0; i < nb_pkts; i++) { - spi = rte_pktmbuf_mtod_offset(pkts[i], struct esp_hdr *, - sizeof(struct ip))->spi; + spi = rte_be_to_cpu_32(rte_pktmbuf_mtod_offset(pkts[i], + struct esp_hdr *, sizeof(struct ip))->spi); if (spi == INVALID_SPI) continue; -- 1.9.1