RDMA/rtrs: Use new shared CQ mechanism
authorJack Wang <jinpu.wang@cloud.ionos.com>
Mon, 22 Feb 2021 14:15:50 +0000 (15:15 +0100)
committerJason Gunthorpe <jgg@nvidia.com>
Thu, 11 Mar 2021 18:50:15 +0000 (14:50 -0400)
commit3b89e92c2a95a39c38a3808f4528e502a39bd94d
treed4484f75751b6b241e3f88739f8c137db5883828
parentf675ba125bd38acb95d84da04e5fd89aa36cc429
RDMA/rtrs: Use new shared CQ mechanism

Have the driver use shared CQs which provids a ~10%-20% improvement during
test.

Instead of opening a CQ for each QP per connection, a CQ for each QP will
be provided by the RDMA core driver that will be shared between the QPs on
that core reducing interrupt overhead.

Link: https://lore.kernel.org/r/20210222141551.54345-1-jinpu.wang@cloud.ionos.com
Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
drivers/infiniband/ulp/rtrs/rtrs-clt.c
drivers/infiniband/ulp/rtrs/rtrs-pri.h
drivers/infiniband/ulp/rtrs/rtrs-srv.c
drivers/infiniband/ulp/rtrs/rtrs.c