net/mlx5: Correctly set gso_segs when LRO is used

When gso_segs is left at 0, a number of assumptions will end up being
incorrect throughout the stack.

For example, in the GRO-path, we set NAPI_GRO_CB()->count to gso_segs.
So, if a non-LRO'ed packet followed by an LRO'ed packet is being
processed in GRO, the first one will have NAPI_GRO_CB()->count set to 1 and
the next one to 0 (in dev_gro_receive()).
Since commit 531d0d3
("net/mlx5: Correctly set gso_size when LRO is used")
these packets will get merged (as their gso_size now matches).
So, we end up in gro_complete() with NAPI_GRO_CB()->count == 1 and thus
don't call inet_gro_complete(). Meaning, checksum-validation in
tcp_checksum_complete() will fail with a "hw csum failure".

Even before the above mentioned commit, incorrect gso_segs means that other
things like TCP's accounting of incoming packets (tp->segs_in,
data_segs_in, rcv_ooopack) will be incorrect. Which means that if one
does bytes_received/data_segs_in, the result will be bigger than the
MTU.

Fix this by initializing gso_segs correctly when LRO is used.

Fixes: e586b3b ("net/mlx5: Ethernet Datapath files")
Reported-by: Gal Pressman <[email protected]>
Closes: https://lore.kernel.org/netdev/[email protected]/
Signed-off-by: Christoph Paasch <[email protected]>
Reviewed-by: Gal Pressman <[email protected]>
Reviewed-by: Eric Dumazet <[email protected]>
Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: cpaasch-oai

drivers/net/ethernet/mellanox/mlx5/core/en_rx.c

@@ -1574,6 +1574,7 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 		unsigned int hdrlen = mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
 
 		skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt - hdrlen, lro_num_seg);
+		skb_shinfo(skb)->gso_segs = lro_num_seg;
 		/* Subtract one since we already counted this as one
 		 * "regular" packet in mlx5e_complete_rx_cqe()
 		 */