From 11f552e21755cb6f804572243a1502b6bbd008dd Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Mon, 10 Jun 2019 15:21:24 +0300 Subject: IB/mlx5: Test write combining support Linux can run in all sorts of physical machines and VMs where write combining may or may not be supported. Currently there is no way to reliably tell if the system supports WC, or not. The driver uses WC to optimize posting work to the HCA, and getting this wrong in either direction can cause a significant performance loss. Add a test in mlx5_ib initialization process to test whether write-combining is supported on the machine. The test will run as part of the enable_driver callback to ensure that the test runs after the device is setup and can create and modify the QP needed, but runs before the device is exposed to the users. The test opens UD QP and posts NOP WQEs, the WQE written to the BlueFlame is different from the WQE in memory, requesting CQE only on the BlueFlame WQE. By checking whether we received a completion on one of these WQEs we can know if BlueFlame succeeded and this write-combining must be supported. Change reporting of BlueFlame support to be dependent on write-combining support instead of the FW's guess as to what the machine can do. Link: https://lore.kernel.org/r/20191027062234.10993-1-leon@kernel.org Signed-off-by: Michael Guralnik Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/main.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 0a8a1a129f17..22db87278c40 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1796,7 +1796,7 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx, return -EINVAL; resp.qp_tab_size = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp); - if (mlx5_core_is_pf(dev->mdev) && MLX5_CAP_GEN(dev->mdev, bf)) + if (dev->wc_support) resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size); resp.cache_line_size = cache_line_size(); resp.max_sq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq); @@ -6256,6 +6256,7 @@ static const struct ib_device_ops mlx5_ib_dev_ops = { .disassociate_ucontext = mlx5_ib_disassociate_ucontext, .drain_rq = mlx5_ib_drain_rq, .drain_sq = mlx5_ib_drain_sq, + .enable_driver = mlx5_ib_enable_driver, .fill_res_entry = mlx5_ib_fill_res_entry, .fill_stat_entry = mlx5_ib_fill_stat_entry, .get_dev_fw_str = get_dev_fw_str, @@ -6699,6 +6700,18 @@ static void mlx5_ib_stage_devx_cleanup(struct mlx5_ib_dev *dev) } } +int mlx5_ib_enable_driver(struct ib_device *dev) +{ + struct mlx5_ib_dev *mdev = to_mdev(dev); + int ret; + + ret = mlx5_ib_test_wc(mdev); + mlx5_ib_dbg(mdev, "Write-Combining %s", + mdev->wc_support ? "supported" : "not supported"); + + return ret; +} + void __mlx5_ib_remove(struct mlx5_ib_dev *dev, const struct mlx5_ib_profile *profile, int stage) -- cgit