From: Sagi Grimberg Date: Tue, 13 Oct 2015 16:11:29 +0000 (+0300) Subject: RDMA/cxgb3: Support the new memory registration API X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=14fb4171ab1c298101697fe844dbf062ff6f4adf;p=GitHub%2FLineageOS%2FG12%2Fandroid_kernel_amlogic_linux-4.9.git RDMA/cxgb3: Support the new memory registration API Support the new memory registration API by allocating a private page list array in iwch_mr and populate it when iwch_map_mr_sg is invoked. Also, support IB_WR_REG_MR by duplicating build_fastreg just take the needed information from different places: - page_size, iova, length (ib_mr) - page array (iwch_mr) - key, access flags (ib_reg_wr) The IB_WR_FAST_REG_MR handlers will be removed later when all the ULPs will be converted. Signed-off-by: Sagi Grimberg Acked-by: Christoph Hellwig Signed-off-by: Doug Ledford --- diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index 93308c45f298..f7b915378343 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -463,6 +463,7 @@ static int iwch_dereg_mr(struct ib_mr *ib_mr) return -EINVAL; mhp = to_iwch_mr(ib_mr); + kfree(mhp->pages); rhp = mhp->rhp; mmid = mhp->attr.stag >> 8; cxio_dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size, @@ -821,6 +822,12 @@ static struct ib_mr *iwch_alloc_mr(struct ib_pd *pd, if (!mhp) goto err; + mhp->pages = kcalloc(max_num_sg, sizeof(u64), GFP_KERNEL); + if (!mhp->pages) { + ret = -ENOMEM; + goto pl_err; + } + mhp->rhp = rhp; ret = iwch_alloc_pbl(mhp, max_num_sg); if (ret) @@ -847,11 +854,36 @@ err3: err2: iwch_free_pbl(mhp); err1: + kfree(mhp->pages); +pl_err: kfree(mhp); err: return ERR_PTR(ret); } +static int iwch_set_page(struct ib_mr *ibmr, u64 addr) +{ + struct iwch_mr *mhp = to_iwch_mr(ibmr); + + if (unlikely(mhp->npages == mhp->attr.pbl_size)) + return -ENOMEM; + + mhp->pages[mhp->npages++] = addr; + + return 0; +} + +static int iwch_map_mr_sg(struct ib_mr *ibmr, + struct scatterlist *sg, + int sg_nents) +{ + struct iwch_mr *mhp = to_iwch_mr(ibmr); + + mhp->npages = 0; + + return ib_sg_to_pages(ibmr, sg, sg_nents, iwch_set_page); +} + static struct ib_fast_reg_page_list *iwch_alloc_fastreg_pbl( struct ib_device *device, int page_list_len) @@ -1450,6 +1482,7 @@ int iwch_register_device(struct iwch_dev *dev) dev->ibdev.bind_mw = iwch_bind_mw; dev->ibdev.dealloc_mw = iwch_dealloc_mw; dev->ibdev.alloc_mr = iwch_alloc_mr; + dev->ibdev.map_mr_sg = iwch_map_mr_sg; dev->ibdev.alloc_fast_reg_page_list = iwch_alloc_fastreg_pbl; dev->ibdev.free_fast_reg_page_list = iwch_free_fastreg_pbl; dev->ibdev.attach_mcast = iwch_multicast_attach; diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.h b/drivers/infiniband/hw/cxgb3/iwch_provider.h index 87c14b0c5ac0..2ac85b86a680 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.h +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.h @@ -77,6 +77,8 @@ struct iwch_mr { struct iwch_dev *rhp; u64 kva; struct tpt_attributes attr; + u64 *pages; + u32 npages; }; typedef struct iwch_mw iwch_mw_handle; diff --git a/drivers/infiniband/hw/cxgb3/iwch_qp.c b/drivers/infiniband/hw/cxgb3/iwch_qp.c index bac0508fedd9..a09ea538e990 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_qp.c +++ b/drivers/infiniband/hw/cxgb3/iwch_qp.c @@ -146,6 +146,49 @@ static int build_rdma_read(union t3_wr *wqe, struct ib_send_wr *wr, return 0; } +static int build_memreg(union t3_wr *wqe, struct ib_reg_wr *wr, + u8 *flit_cnt, int *wr_cnt, struct t3_wq *wq) +{ + struct iwch_mr *mhp = to_iwch_mr(wr->mr); + int i; + __be64 *p; + + if (mhp->npages > T3_MAX_FASTREG_DEPTH) + return -EINVAL; + *wr_cnt = 1; + wqe->fastreg.stag = cpu_to_be32(wr->key); + wqe->fastreg.len = cpu_to_be32(mhp->ibmr.length); + wqe->fastreg.va_base_hi = cpu_to_be32(mhp->ibmr.iova >> 32); + wqe->fastreg.va_base_lo_fbo = + cpu_to_be32(mhp->ibmr.iova & 0xffffffff); + wqe->fastreg.page_type_perms = cpu_to_be32( + V_FR_PAGE_COUNT(mhp->npages) | + V_FR_PAGE_SIZE(ilog2(wr->mr->page_size) - 12) | + V_FR_TYPE(TPT_VATO) | + V_FR_PERMS(iwch_ib_to_tpt_access(wr->access))); + p = &wqe->fastreg.pbl_addrs[0]; + for (i = 0; i < mhp->npages; i++, p++) { + + /* If we need a 2nd WR, then set it up */ + if (i == T3_MAX_FASTREG_FRAG) { + *wr_cnt = 2; + wqe = (union t3_wr *)(wq->queue + + Q_PTR2IDX((wq->wptr+1), wq->size_log2)); + build_fw_riwrh((void *)wqe, T3_WR_FASTREG, 0, + Q_GENBIT(wq->wptr + 1, wq->size_log2), + 0, 1 + mhp->npages - T3_MAX_FASTREG_FRAG, + T3_EOP); + + p = &wqe->pbl_frag.pbl_addrs[0]; + } + *p = cpu_to_be64((u64)mhp->pages[i]); + } + *flit_cnt = 5 + mhp->npages; + if (*flit_cnt > 15) + *flit_cnt = 15; + return 0; +} + static int build_fastreg(union t3_wr *wqe, struct ib_send_wr *send_wr, u8 *flit_cnt, int *wr_cnt, struct t3_wq *wq) { @@ -419,6 +462,11 @@ int iwch_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, err = build_fastreg(wqe, wr, &t3_wr_flit_cnt, &wr_cnt, &qhp->wq); break; + case IB_WR_REG_MR: + t3_wr_opcode = T3_WR_FASTREG; + err = build_memreg(wqe, reg_wr(wr), &t3_wr_flit_cnt, + &wr_cnt, &qhp->wq); + break; case IB_WR_LOCAL_INV: if (wr->send_flags & IB_SEND_FENCE) t3_wr_flags |= T3_LOCAL_FENCE_FLAG;