RDMA/mlx5: Expose register c0 for RDMA device
authorMark Bloch <mbloch@nvidia.com>
Wed, 6 Dec 2023 14:01:38 +0000 (16:01 +0200)
committerLeon Romanovsky <leon@kernel.org>
Tue, 12 Dec 2023 07:04:07 +0000 (09:04 +0200)
commitd727d27db536faea7178290c677cc0567f647231
tree1baa5420e185873af4cc5e121a360ce37d4cc9f3
parenteb524d0fd46249b0b9e5d52372dc65d8b32430c3
RDMA/mlx5: Expose register c0 for RDMA device

This patch introduces improvements for matching egress traffic sent by the
local device. When applicable, all egress traffic from the local vport is
now tagged with the provided value. This enhancement is particularly useful
for FDB steering purposes.

The primary focus of this update is facilitating the transmission of
traffic from the hypervisor to a VF. To achieve this, one must initiate an
SQ on the hypervisor and subsequently create a rule in the FDB that matches
on the eswitch manager vport and the SQN of the aforementioned SQ.

Obtaining the SQN can be had from SQ opened, and the eswitch manager vport
match can be substituted with the register c0 value exposed by this patch.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Link: https://lore.kernel.org/r/aa4120a91c98ff1c44f1213388c744d4cb0324d6.1701871118.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
drivers/infiniband/hw/mlx5/main.c
include/uapi/rdma/mlx5-abi.h