RDMA/ocrdma: Support the new memory registration API

Support the new memory registration API by allocating a
private page list array in ocrdma_mr and populate it when
ocrdma_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by duplicating IB_WR_FAST_REG_MR, but take the needed
information from different places:
- page_size, iova, length, access flags (ib_mr)
- page array (ocrdma_mr)
- key (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 <sagig@mellanox.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Doug Ledford <dledford@redhat.com>

diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h
index 8f047f996e220a5e682eaca43cea24cfeb21e3f0..ae80590aabdf7db6df756c0ee07afa4721f6c37c 100644 (file)
--- a/drivers/infiniband/hw/ocrdma/ocrdma.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma.h
@@ -193,6 +193,8 @@ struct ocrdma_mr {
        struct ib_mr ibmr;
        struct ib_umem *umem;
        struct ocrdma_hw_mr hwmr;
+       u64 *pages;
+       u32 npages;
 };
 
 struct ocrdma_stats {

diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index cb1af0fb405145e60c60f7f3c9b1f91f273dfdf2..19a5ccd6e5fc7332ee46b9e0e89d6365de15e25e 100644 (file)
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -180,6 +180,7 @@ static int ocrdma_register_device(struct ocrdma_dev *dev)
        dev->ibdev.reg_user_mr = ocrdma_reg_user_mr;
 
        dev->ibdev.alloc_mr = ocrdma_alloc_mr;
+       dev->ibdev.map_mr_sg = ocrdma_map_mr_sg;
        dev->ibdev.alloc_fast_reg_page_list = ocrdma_alloc_frmr_page_list;
        dev->ibdev.free_fast_reg_page_list = ocrdma_free_frmr_page_list;
 

diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index dd00219b7d15e4a667fa35686772a86fbbf65ffc..49481dfaa49398108cb94b937ccb0e5b816beca3 100644 (file)
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -1013,6 +1013,7 @@ int ocrdma_dereg_mr(struct ib_mr *ib_mr)
 
        (void) ocrdma_mbx_dealloc_lkey(dev, mr->hwmr.fr_mr, mr->hwmr.lkey);
 
+       kfree(mr->pages);
        ocrdma_free_mr_pbl_tbl(dev, &mr->hwmr);
 
        /* it could be user registered memory. */
@@ -2177,6 +2178,61 @@ static int get_encoded_page_size(int pg_sz)
        return i;
 }
 
+static int ocrdma_build_reg(struct ocrdma_qp *qp,
+                           struct ocrdma_hdr_wqe *hdr,
+                           struct ib_reg_wr *wr)
+{
+       u64 fbo;
+       struct ocrdma_ewqe_fr *fast_reg = (struct ocrdma_ewqe_fr *)(hdr + 1);
+       struct ocrdma_mr *mr = get_ocrdma_mr(wr->mr);
+       struct ocrdma_pbl *pbl_tbl = mr->hwmr.pbl_table;
+       struct ocrdma_pbe *pbe;
+       u32 wqe_size = sizeof(*fast_reg) + sizeof(*hdr);
+       int num_pbes = 0, i;
+
+       wqe_size = roundup(wqe_size, OCRDMA_WQE_ALIGN_BYTES);
+
+       hdr->cw |= (OCRDMA_FR_MR << OCRDMA_WQE_OPCODE_SHIFT);
+       hdr->cw |= ((wqe_size / OCRDMA_WQE_STRIDE) << OCRDMA_WQE_SIZE_SHIFT);
+
+       if (wr->access & IB_ACCESS_LOCAL_WRITE)
+               hdr->rsvd_lkey_flags |= OCRDMA_LKEY_FLAG_LOCAL_WR;
+       if (wr->access & IB_ACCESS_REMOTE_WRITE)
+               hdr->rsvd_lkey_flags |= OCRDMA_LKEY_FLAG_REMOTE_WR;
+       if (wr->access & IB_ACCESS_REMOTE_READ)
+               hdr->rsvd_lkey_flags |= OCRDMA_LKEY_FLAG_REMOTE_RD;
+       hdr->lkey = wr->key;
+       hdr->total_len = mr->ibmr.length;
+
+       fbo = mr->ibmr.iova - mr->pages[0];
+
+       fast_reg->va_hi = upper_32_bits(mr->ibmr.iova);
+       fast_reg->va_lo = (u32) (mr->ibmr.iova & 0xffffffff);
+       fast_reg->fbo_hi = upper_32_bits(fbo);
+       fast_reg->fbo_lo = (u32) fbo & 0xffffffff;
+       fast_reg->num_sges = mr->npages;
+       fast_reg->size_sge = get_encoded_page_size(mr->ibmr.page_size);
+
+       pbe = pbl_tbl->va;
+       for (i = 0; i < mr->npages; i++) {
+               u64 buf_addr = mr->pages[i];
+
+               pbe->pa_lo = cpu_to_le32((u32) (buf_addr & PAGE_MASK));
+               pbe->pa_hi = cpu_to_le32((u32) upper_32_bits(buf_addr));
+               num_pbes += 1;
+               pbe++;
+
+               /* if the pbl is full storing the pbes,
+                * move to next pbl.
+               */
+               if (num_pbes == (mr->hwmr.pbl_size/sizeof(u64))) {
+                       pbl_tbl++;
+                       pbe = (struct ocrdma_pbe *)pbl_tbl->va;
+               }
+       }
+
+       return 0;
+}
 
 static int ocrdma_build_fr(struct ocrdma_qp *qp, struct ocrdma_hdr_wqe *hdr,
                           struct ib_send_wr *send_wr)
@@ -2304,6 +2360,9 @@ int ocrdma_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
                case IB_WR_FAST_REG_MR:
                        status = ocrdma_build_fr(qp, hdr, wr);
                        break;
+               case IB_WR_REG_MR:
+                       status = ocrdma_build_reg(qp, hdr, reg_wr(wr));
+                       break;
                default:
                        status = -EINVAL;
                        break;
@@ -3054,6 +3113,12 @@ struct ib_mr *ocrdma_alloc_mr(struct ib_pd *ibpd,
        if (!mr)
                return ERR_PTR(-ENOMEM);
 
+       mr->pages = kcalloc(max_num_sg, sizeof(u64), GFP_KERNEL);
+       if (!mr->pages) {
+               status = -ENOMEM;
+               goto pl_err;
+       }
+
        status = ocrdma_get_pbl_info(dev, mr, max_num_sg);
        if (status)
                goto pbl_err;
@@ -3077,6 +3142,8 @@ struct ib_mr *ocrdma_alloc_mr(struct ib_pd *ibpd,
 mbx_err:
        ocrdma_free_mr_pbl_tbl(dev, &mr->hwmr);
 pbl_err:
+       kfree(mr->pages);
+pl_err:
        kfree(mr);
        return ERR_PTR(-ENOMEM);
 }
@@ -3263,3 +3330,26 @@ pbl_err:
        kfree(mr);
        return ERR_PTR(status);
 }
+
+static int ocrdma_set_page(struct ib_mr *ibmr, u64 addr)
+{
+       struct ocrdma_mr *mr = get_ocrdma_mr(ibmr);
+
+       if (unlikely(mr->npages == mr->hwmr.num_pbes))
+               return -ENOMEM;
+
+       mr->pages[mr->npages++] = addr;
+
+       return 0;
+}
+
+int ocrdma_map_mr_sg(struct ib_mr *ibmr,
+                    struct scatterlist *sg,
+                    int sg_nents)
+{
+       struct ocrdma_mr *mr = get_ocrdma_mr(ibmr);
+
+       mr->npages = 0;
+
+       return ib_sg_to_pages(ibmr, sg, sg_nents, ocrdma_set_page);
+}

diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
index 308c16857a5d03e2d3605136abdf8d3b11ad5361..1b2d3ac10203912bfb53e680d07d0e87c8724d55 100644 (file)
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
@@ -125,6 +125,9 @@ struct ib_mr *ocrdma_reg_user_mr(struct ib_pd *, u64 start, u64 length,
 struct ib_mr *ocrdma_alloc_mr(struct ib_pd *pd,
                              enum ib_mr_type mr_type,
                              u32 max_num_sg);
+int ocrdma_map_mr_sg(struct ib_mr *ibmr,
+                    struct scatterlist *sg,
+                    int sg_nents);
 struct ib_fast_reg_page_list *ocrdma_alloc_frmr_page_list(struct ib_device
                                                        *ibdev,
                                                        int page_list_len);