net/mlx5e: Fix TCP checksum in LRO buffers

When receiving an LRO packet, the checksum field is set by the hardware
to the checksum of the first coalesced packet. Obviously, this checksum
is not valid for the merged LRO packet and should be fixed.  We can use
the CQE checksum which covers the checksum of the entire merged packet
TCP payload to help us calculate the checksum incrementally.

Tested by sending IPv4/6 traffic with LRO enabled, RX checksum disabled
and watching nstat checksum error counters (in addition to the obvious
bandwidth drop caused by checksum errors).

This bug is usually "hidden" since LRO packets would go through the
CHECKSUM_UNNECESSARY flow which does not validate the packet checksum.

It's important to note that previous to this patch, LRO packets provided
with CHECKSUM_UNNECESSARY are indeed packets with a correct validated
checksum (even though the checksum inside the TCP header is incorrect),
since the hardware LRO aggregation is terminated upon receiving a packet
with bad checksum.

Fixes: e586b3b0baee ("net/mlx5: Ethernet Datapath files")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 0d4bb0688faa1349913d25c13f2366b130a06682..e5c3ab46a24a5134de9349a8e761504cfa49a33d 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -36,6 +36,7 @@
 #include <linux/tcp.h>
 #include <linux/bpf_trace.h>
 #include <net/busy_poll.h>
+#include <net/ip6_checksum.h>
 #include "en.h"
 #include "en_tc.h"
 #include "eswitch.h"
@@ -546,20 +547,33 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
        return true;
 }
 
+static void mlx5e_lro_update_tcp_hdr(struct mlx5_cqe64 *cqe, struct tcphdr *tcp)
+{
+       u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
+       u8 tcp_ack     = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) ||
+                        (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA);
+
+       tcp->check                      = 0;
+       tcp->psh                        = get_cqe_lro_tcppsh(cqe);
+
+       if (tcp_ack) {
+               tcp->ack                = 1;
+               tcp->ack_seq            = cqe->lro_ack_seq_num;
+               tcp->window             = cqe->lro_tcp_win;
+       }
+}
+
 static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
                                 u32 cqe_bcnt)
 {
        struct ethhdr   *eth = (struct ethhdr *)(skb->data);
        struct tcphdr   *tcp;
        int network_depth = 0;
+       __wsum check;
        __be16 proto;
        u16 tot_len;
        void *ip_p;
 
-       u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
-       u8 tcp_ack = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) ||
-               (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA);
-
        proto = __vlan_get_protocol(skb, eth->h_proto, &network_depth);
 
        tot_len = cqe_bcnt - network_depth;
@@ -576,23 +590,30 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
                ipv4->check             = 0;
                ipv4->check             = ip_fast_csum((unsigned char *)ipv4,
                                                       ipv4->ihl);
+
+               mlx5e_lro_update_tcp_hdr(cqe, tcp);
+               check = csum_partial(tcp, tcp->doff * 4,
+                                    csum_unfold((__force __sum16)cqe->check_sum));
+               /* Almost done, don't forget the pseudo header */
+               tcp->check = csum_tcpudp_magic(ipv4->saddr, ipv4->daddr,
+                                              tot_len - sizeof(struct iphdr),
+                                              IPPROTO_TCP, check);
        } else {
+               u16 payload_len = tot_len - sizeof(struct ipv6hdr);
                struct ipv6hdr *ipv6 = ip_p;
 
                tcp = ip_p + sizeof(struct ipv6hdr);
                skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 
                ipv6->hop_limit         = cqe->lro_min_ttl;
-               ipv6->payload_len       = cpu_to_be16(tot_len -
-                                                     sizeof(struct ipv6hdr));
-       }
-
-       tcp->psh = get_cqe_lro_tcppsh(cqe);
-
-       if (tcp_ack) {
-               tcp->ack                = 1;
-               tcp->ack_seq            = cqe->lro_ack_seq_num;
-               tcp->window             = cqe->lro_tcp_win;
+               ipv6->payload_len       = cpu_to_be16(payload_len);
+
+               mlx5e_lro_update_tcp_hdr(cqe, tcp);
+               check = csum_partial(tcp, tcp->doff * 4,
+                                    csum_unfold((__force __sum16)cqe->check_sum));
+               /* Almost done, don't forget the pseudo header */
+               tcp->check = csum_ipv6_magic(&ipv6->saddr, &ipv6->daddr, payload_len,
+                                            IPPROTO_TCP, check);
        }
 }