From: Emeel Hakim ehakim@nvidia.com
[ Upstream commit d10457f85d4ae4d32c0df0cd65358a78c577fbe6 ]
IPsec crypto offload current Software Parser (SWP) fields settings in the ethernet segment (eseg) are not aligned with PRM/HW expectations. Among others in case of IP|ESP|TCP packet, current driver sets the offsets for inner_l3 and inner_l4 although there is no inner l3/l4 headers relative to ESP header in such packets.
SWP provides the offsets for HW ,so it can be used to find csum fields to offload the checksum, however these are not necessarily used by HW and are used as fallback in case HW fails to parse the packet, e.g when performing IPSec Transport Aware (IP | ESP | TCP) there is no need to add SW parse on inner packet. So in some cases packets csum was calculated correctly , whereas in other cases it failed. The later faced csum errors (caused by wrong packet length calculations) which led to lots of packet drops hence the low throughput.
Fix by setting the SWP fields as expected in a IP|ESP|TCP packet.
the following describe the expected SWP offsets: * Tunnel Mode: * SWP: OutL3 InL3 InL4 * Pkt: MAC IP ESP IP L4 * * Transport Mode: * SWP: OutL3 OutL4 * Pkt: MAC IP ESP L4 * * Tunnel(VXLAN TCP/UDP) over Transport Mode * SWP: OutL3 InL3 InL4 * Pkt: MAC IP ESP UDP VXLAN IP L4
Fixes: f1267798c980 ("net/mlx5: Fix checksum issue of VXLAN and IPsec crypto offload") Signed-off-by: Emeel Hakim ehakim@nvidia.com Reviewed-by: Raed Salem raeds@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../mellanox/mlx5/core/en_accel/ipsec_rxtx.c | 51 ++++++++++--------- 1 file changed, 27 insertions(+), 24 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 33de8f0092a6..fb5397324aa4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -141,8 +141,7 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb, * Pkt: MAC IP ESP IP L4 * * Transport Mode: - * SWP: OutL3 InL4 - * InL3 + * SWP: OutL3 OutL4 * Pkt: MAC IP ESP L4 * * Tunnel(VXLAN TCP/UDP) over Transport Mode @@ -171,31 +170,35 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb, return;
if (!xo->inner_ipproto) { - eseg->swp_inner_l3_offset = skb_network_offset(skb) / 2; - eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2; - if (skb->protocol == htons(ETH_P_IPV6)) - eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; - if (xo->proto == IPPROTO_UDP) + switch (xo->proto) { + case IPPROTO_UDP: + eseg->swp_flags |= MLX5_ETH_WQE_SWP_OUTER_L4_UDP; + fallthrough; + case IPPROTO_TCP: + /* IP | ESP | TCP */ + eseg->swp_outer_l4_offset = skb_inner_transport_offset(skb) / 2; + break; + default: + break; + } + } else { + /* Tunnel(VXLAN TCP/UDP) over Transport Mode */ + switch (xo->inner_ipproto) { + case IPPROTO_UDP: eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP; - return; - } - - /* Tunnel(VXLAN TCP/UDP) over Transport Mode */ - switch (xo->inner_ipproto) { - case IPPROTO_UDP: - eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP; - fallthrough; - case IPPROTO_TCP: - eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2; - eseg->swp_inner_l4_offset = (skb->csum_start + skb->head - skb->data) / 2; - if (skb->protocol == htons(ETH_P_IPV6)) - eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; - break; - default: - break; + fallthrough; + case IPPROTO_TCP: + eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2; + eseg->swp_inner_l4_offset = + (skb->csum_start + skb->head - skb->data) / 2; + if (skb->protocol == htons(ETH_P_IPV6)) + eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; + break; + default: + break; + } }
- return; }
void mlx5e_ipsec_set_iv_esn(struct sk_buff *skb, struct xfrm_state *x,