From: Leon Romanovsky <leonro@xxxxxxxxxx> >From Avihai, Relaxed Ordering is a PCIe mechanism that relaxes the strict ordering imposed on PCI transactions, and thus, can improve performance. Until now, relaxed ordering could be set only by user space applications for user MRs. The following patch series enables relaxed ordering for the kernel ULPs as well. Relaxed ordering is an optional capability, and as such, it is ignored by vendors that don't support it. The following test results show the performance improvement achieved with relaxed ordering. The test was performed on a NVIDIA A100 in order to check performance of storage infrastructure over xprtrdma: Without Relaxed Ordering: READ: bw=16.5GiB/s (17.7GB/s), 16.5GiB/s-16.5GiB/s (17.7GB/s-17.7GB/s), io=1987GiB (2133GB), run=120422-120422msec With relaxed ordering: READ: bw=72.9GiB/s (78.2GB/s), 72.9GiB/s-72.9GiB/s (78.2GB/s-78.2GB/s), io=2367GiB (2542GB), run=32492-32492msec Thanks Avihai Horon (10): RDMA: Add access flags to ib_alloc_mr() and ib_mr_pool_init() RDMA/core: Enable Relaxed Ordering in __ib_alloc_pd() RDMA/iser: Enable Relaxed Ordering RDMA/rtrs: Enable Relaxed Ordering RDMA/srp: Enable Relaxed Ordering nvme-rdma: Enable Relaxed Ordering cifs: smbd: Enable Relaxed Ordering net/rds: Enable Relaxed Ordering net/smc: Enable Relaxed Ordering xprtrdma: Enable Relaxed Ordering drivers/infiniband/core/mr_pool.c | 7 +- drivers/infiniband/core/rw.c | 12 ++-- drivers/infiniband/core/verbs.c | 26 +++++-- drivers/infiniband/hw/bnxt_re/ib_verbs.c | 2 +- drivers/infiniband/hw/bnxt_re/ib_verbs.h | 2 +- drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 2 +- drivers/infiniband/hw/cxgb4/mem.c | 2 +- drivers/infiniband/hw/hns/hns_roce_device.h | 2 +- drivers/infiniband/hw/hns/hns_roce_mr.c | 2 +- drivers/infiniband/hw/i40iw/i40iw_verbs.c | 3 +- drivers/infiniband/hw/mlx4/mlx4_ib.h | 2 +- drivers/infiniband/hw/mlx4/mr.c | 2 +- drivers/infiniband/hw/mlx5/mlx5_ib.h | 12 ++-- drivers/infiniband/hw/mlx5/mr.c | 61 ++++++++-------- drivers/infiniband/hw/mlx5/wr.c | 69 ++++++++++++++----- drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 2 +- drivers/infiniband/hw/ocrdma/ocrdma_verbs.h | 2 +- drivers/infiniband/hw/qedr/verbs.c | 2 +- drivers/infiniband/hw/qedr/verbs.h | 2 +- drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c | 4 +- .../infiniband/hw/vmw_pvrdma/pvrdma_verbs.h | 2 +- drivers/infiniband/sw/rdmavt/mr.c | 3 +- drivers/infiniband/sw/rdmavt/mr.h | 2 +- drivers/infiniband/sw/rxe/rxe_verbs.c | 2 +- drivers/infiniband/sw/siw/siw_verbs.c | 2 +- drivers/infiniband/sw/siw/siw_verbs.h | 2 +- drivers/infiniband/ulp/iser/iser_memory.c | 10 ++- drivers/infiniband/ulp/iser/iser_verbs.c | 6 +- drivers/infiniband/ulp/rtrs/rtrs-clt.c | 6 +- drivers/infiniband/ulp/rtrs/rtrs-srv.c | 15 ++-- drivers/infiniband/ulp/srp/ib_srp.c | 8 +-- drivers/nvme/host/rdma.c | 19 +++-- fs/cifs/smbdirect.c | 17 +++-- include/rdma/ib_verbs.h | 11 ++- include/rdma/mr_pool.h | 3 +- net/rds/ib_frmr.c | 7 +- net/smc/smc_ib.c | 3 +- net/smc/smc_wr.c | 3 +- net/sunrpc/xprtrdma/frwr_ops.c | 10 +-- 39 files changed, 209 insertions(+), 140 deletions(-) -- 2.30.2
