From 4d4fb5dc988a36307711be292bde6e39b8bdbceb Mon Sep 17 00:00:00 2001 From: Yonatan Cohen Date: Tue, 19 Jun 2018 08:47:22 +0300 Subject: net/mlx5: Limit scope of dump_fill_mkey function mlx5_core_dump_fill_mkey() is going to be used in next patch in IB and doesn't need to be visible to whole mlx5_core. Move that command to mlx5_ib. Signed-off-by: Yonatan Cohen Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 80cbb7fdce4a..1cb1c0317b77 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1067,8 +1067,6 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey); int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, u32 *out, int outlen); -int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *_mkey, - u32 *mkey); int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn); int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn); int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, -- cgit v1.2.3 From b183ee27f5fb07c8428e2fe45d5f35dac611c45d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 19 Jun 2018 08:47:23 +0300 Subject: net/mlx5: Add hardware definitions for dump_fill_mkey MLX5 IB HCA offers the memory key, dump_fill_mkey to boost performance by forcing local HCA operations to skip the PCI bus access, This patch adds needed hardware definitions. Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index deb3a459a22e..1853e7fd6924 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -885,7 +885,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_eq_sz[0x8]; u8 reserved_at_e8[0x2]; u8 log_max_mkey[0x6]; - u8 reserved_at_f0[0xc]; + u8 reserved_at_f0[0x8]; + u8 dump_fill_mkey[0x1]; + u8 reserved_at_f9[0x3]; u8 log_max_eq[0x4]; u8 max_indirection[0x8]; -- cgit v1.2.3 From 25bb36e75d7d62dc14ae2306dca38d672e0c3fa0 Mon Sep 17 00:00:00 2001 From: Yonatan Cohen Date: Tue, 19 Jun 2018 08:47:24 +0300 Subject: IB/mlx5: Expose dump and fill memory key MLX5 IB HCA offers the memory key, dump_fill_mkey to boost performance, when used in a send or receive operations. It is used to force local HCA operations to skip the PCI bus access, while keeping track of the processed length in the ibv_sge handling. Meaning, instead of a PCI write access the HCA leaves the target memory untouched, and skips filling that packet section. Similar behavior is done upon send, the HCA skips data in memory relevant to this key and saves PCI bus access. This functionality saves PCI read/write operations. Signed-off-by: Yonatan Cohen Reviewed-by: Yishai Hadas Reviewed-by: Guy Levi Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/main.c | 16 ++++++++++++++++ include/uapi/rdma/mlx5-abi.h | 3 ++- 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index e52dd21519b4..bd402691c2c0 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1660,6 +1660,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, int err; size_t min_req_v2 = offsetof(struct mlx5_ib_alloc_ucontext_req_v2, max_cqe_version); + u32 dump_fill_mkey; bool lib_uar_4k; if (!dev->ib_active) @@ -1761,6 +1762,12 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, goto out_uars; } + if (MLX5_CAP_GEN(dev->mdev, dump_fill_mkey)) { + err = mlx5_cmd_dump_fill_mkey(dev->mdev, &dump_fill_mkey); + if (err) + goto out_td; + } + INIT_LIST_HEAD(&context->vma_private_list); mutex_init(&context->vma_private_list_mutex); INIT_LIST_HEAD(&context->db_page_list); @@ -1819,6 +1826,15 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, resp.response_length += sizeof(resp.num_dyn_bfregs); } + if (field_avail(typeof(resp), dump_fill_mkey, udata->outlen)) { + if (MLX5_CAP_GEN(dev->mdev, dump_fill_mkey)) { + resp.dump_fill_mkey = dump_fill_mkey; + resp.comp_mask |= + MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_DUMP_FILL_MKEY; + } + resp.response_length += sizeof(resp.dump_fill_mkey); + } + err = ib_copy_to_udata(udata, &resp, resp.response_length); if (err) goto out_td; diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h index 8daec1fa49cf..1f7b7b6bddf0 100644 --- a/include/uapi/rdma/mlx5-abi.h +++ b/include/uapi/rdma/mlx5-abi.h @@ -90,6 +90,7 @@ struct mlx5_ib_alloc_ucontext_req_v2 { enum mlx5_ib_alloc_ucontext_resp_mask { MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET = 1UL << 0, + MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_DUMP_FILL_MKEY = 1UL << 1, }; enum mlx5_user_cmds_supp_uhw { @@ -138,7 +139,7 @@ struct mlx5_ib_alloc_ucontext_resp { __u32 log_uar_size; __u32 num_uars_per_page; __u32 num_dyn_bfregs; - __u32 reserved3; + __u32 dump_fill_mkey; }; struct mlx5_ib_alloc_pd_resp { -- cgit v1.2.3